https://www.aclweb.org/aclwiki/api.php?action=feedcontributions&feedformat=atom&user=SivareddyACL Wiki - User contributions [en]2026-04-18T20:46:28ZUser contributionsMediaWiki 1.43.6https://www.aclweb.org/aclwiki/index.php?title=Resources_for_Hindi&diff=10794Resources for Hindi2014-06-30T15:18:37Z<p>Sivareddy: </p>
<hr />
<div>Hindi computing is gaining momentum very fast. thousands of Hindi sites, blogs and portals have come as a result of availability of computing tools and ease of use. Following link has a list of important tools and softwares for Hindi and Devanaagarii:<br />
<br />
*[http://bit.ly/ytAT95 Hindi Computing : Tools and Techniques]<br />
<br />
==Corpora==<br />
<br />
* [http://ufal.mff.cuni.cz/hamledt HamleDT], harmonized dependency treebanks of many languages, common annotation style.<br />
<br />
==Dependency Parser==<br />
<br />
* [http://sivareddy.in/downloads Download the Parser]<br />
* [http://sivareddy.in/papers/files/hindi.dependency.parser.out.pdf Sample output of the parser]<br />
<br />
==POS Tagger, Morphological Analyzer, Lemmatizer, Corpus==<br />
<br />
* [http://sivareddy.in/downloads Download the tagger]<br />
<br />
* [http://sivareddy.in/papers/files/hindi.sample.out.pdf Sample output of the tagger]<br />
<br />
The tagger and its related files are distributed under GNU GPL license. Corpus is licensed.<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://www.aclweb.org/anthology-new/W/W11/W11-3603.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Morphological analysis==<br />
<br />
===Free software===<br />
<br />
* [http://apertium.svn.sourceforge.net/svnroot/apertium/trunk/incubator/apertium-hi-ur.hi.dix Hindi analyser] for [[lttoolbox]] (~29,385 lemmata) -- GPL (by the University of Hyderabad &mdash; converted from the Anusaaraka analyser)<br />
<br />
==Machine translation==<br />
<br />
===Free software===<br />
<br />
* [http://ltrc.iiit.net/~anusaaraka/ Anusaaraka] Hindi&mdash;English and others.<br />
<br />
==Shallow Parser==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Hindi Shallow parser]<br />
<br />
Keywords: Hindi, Part of Speech tagger, Lemmatizer, Morph Analyzer, Corpus<br />
<br />
[[Category:Resources by language|Hindi]]<br />
[[Category: Part of Speech tagger]]<br />
[[Category: Lemmatizer]]<br />
[[Category: Morph Analyser]]<br />
[[Category: Corpus]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Hindi&diff=10002Resources for Hindi2013-04-20T19:11:48Z<p>Sivareddy: </p>
<hr />
<div>Hindi computing is gaining momentum very fast. thousands of Hindi sites, blogs and portals have come as a result of availability of computing tools and ease of use. Following link has a list of important tools and softwares for Hindi and Devanaagarii:<br />
<br />
*[http://bit.ly/ytAT95 Hindi Computing : Tools and Techniques]<br />
<br />
==Dependency Parser==<br />
<br />
* [http://sivareddy.in/downloads Download the Parser]<br />
* [http://sivareddy.in/papers/files/hindi.dependency.parser.out.txt Sample output of the parser]<br />
<br />
==POS Tagger, Morphological Analyzer, Lemmatizer, Corpus==<br />
<br />
* [http://sivareddy.in/downloads Download the tagger]<br />
<br />
* [http://sivareddy.in/papers/files/hindi.sample.out.txt Sample output of the tagger]<br />
<br />
The tagger and its related files are distributed under GNU GPL license. Corpus is licensed.<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://www.aclweb.org/anthology-new/W/W11/W11-3603.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Morphological analysis==<br />
<br />
===Free software===<br />
<br />
* [http://apertium.svn.sourceforge.net/svnroot/apertium/trunk/incubator/apertium-hi-ur.hi.dix Hindi analyser] for [[lttoolbox]] (~29,385 lemmata) -- GPL (by the University of Hyderabad &mdash; converted from the Anusaaraka analyser)<br />
<br />
==Machine translation==<br />
<br />
===Free software===<br />
<br />
* [http://ltrc.iiit.net/~anusaaraka/ Anusaaraka] Hindi&mdash;English and others.<br />
<br />
==Shallow Parser==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Hindi Shallow parser]<br />
<br />
Keywords: Hindi, Part of Speech tagger, Lemmatizer, Morph Analyzer, Corpus<br />
<br />
[[Category:Resources by language|Hindi]]<br />
[[Category: Part of Speech tagger]]<br />
[[Category: Lemmatizer]]<br />
[[Category: Morph Analyser]]<br />
[[Category: Corpus]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=User:Sivareddy&diff=9340User:Sivareddy2012-05-11T18:21:03Z<p>Sivareddy: </p>
<hr />
<div>Name: Siva Reddy<br />
<br />
Webpage: http://sivareddy.in<br />
<br />
CV: http://sivareddy.in/cv_siva.pdf<br />
<br />
Research Interests: Lexical Semantics, Semantic Composition, Multiwords, Machine Learning, Word Sense Disambiguation/Induction, Lexical Acquisition, Web Corpora, Web as a Resource for NLP problems, Cross Language Resources, Syntactic Parsing, Question Answering Inference<br />
<br />
Please find some of the resources developed by me.<br />
<br />
== Compound Noun Compositionality Dataset ==<br />
<br />
[http://sivareddy.in/papers/files/ijcnlp_compositionality_data.tgz '''Compositionality Dataset'''] described in [http://sivareddy.in/papers/ijcnlp2011empirical.pdf Reddy, McCarthy and Manandhar (2011, IJCNLP)]. [http://dianamccarthy.co.uk/downloads.html Alternate download link] from [http://dianamccarthy.co.uk/ Diana McCarthy]<br />
<br />
== POS Taggers, Corpora, Lemmatizers, Morph Analyzers for Indian Languages ==<br />
<br />
Most of these tools are developed by the methods described in [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Reddy and Sharoff (2011, CLIA @ IJCNLP)]. Some of the taggers are built using cross-lingual resources and some using mono-lingual resources. Please read corresponding README's of each tool for additional information. This work is supported by [http://sketchengine.co.uk Sketch Engine] and [http://corpus.leeds.ac.uk/it/ Intellitext project]. If you need resources for any other Indian languages, please contact me.<br />
<br />
=== Kannada Tools ===<br />
<br />
[http://sivareddy.in/papers/files/kannada-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/kannada.sample.out.txt Sample Output of the tagger] For the complete corpus described in the paper, please contact me. [http://corpus.leeds.ac.uk/tools/ Alternate download link] from [http://www.comp.leeds.ac.uk/ssharoff/ Serge Sharoff]<br />
<br />
=== Telugu Tools ===<br />
<br />
[http://sivareddy.in/papers/files/telugu-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/telugu.sample.out.txt Sample Output of the tagger]<br />
<br />
=== Hindi Tools ===<br />
<br />
[http://sivareddy.in/papers/files/hindi-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/hindi.sample.out.txt Sample Output of the tagger] <br />
<br />
== Indonesian and Malay morphological analyzer, part-of-speech (POS) tagger, Machine Translation System ==<br />
<br />
With support from [http://sketchengine.co.uk Sketch Engine], I have made few contributions to the [http://wiki.apertium.org/wiki/Main_Page Apertium] Indonesian-Malay language pair. All the tools can be downloaded from svn repository https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms/ To download use the command "svn co https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms/" <br /><br />
<br />
----<br />
<br />
Keywords: [[Polysemy]], [[Compositionality]], [[Semantic Composition]], [[Domain WSD]], [[Vector Space Models]], [[Semantics]], IIIT Hyderabad, York, Lexical Computing Ltd., [[Sketch Engine]], [[Resources]], [[POS Taggers]], [[Morphological Analyzers]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Sketch_Engine&diff=9339Sketch Engine2012-05-11T18:19:50Z<p>Sivareddy: </p>
<hr />
<div>== Background ==<br />
The Sketch Engine is a web-based program which takes as its input a corpus of any language with an appropriate level of linguistic mark-up. The Sketch Engine has a number of language-analysis functions, the core ones being:<br />
* '''the Concordancer''' A program which displays all occurrences from the corpus for a given query. The program is very powerful with a wide variety of query types and many different ways of displaying and organising the results.<br />
* '''the Word Sketch program''' This program provides a corpus-based summary of a word's grammatical and collocational behaviour. It will be described below in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted/#wordsketchid section 5].<br />
<br />
For the purposes of this guide, we use examples based on the Sketch Engine loaded with a sample corpus of English, the British National Corpus (BNC). For more information about the Sketch Engine, see [https://trac.sketchengine.co.uk/wiki/SkE/DocsIndex:sketch-engine-elx04.pdf Kilgarriff et al 2004 in Proc EURALEX]. For more information about the BNC, see [http://www.natcorp.ox.ac.uk/ http://www.natcorp.ox.ac.uk/]. <br />
<br />
<br />
Most terminology is defined as it is encountered below, however for a full glossary please see our [https://trac.sketchengine.co.uk/wiki/SkE/Help/JargonBuster Jargon Buster]<br />
<br />
<br />
== Home page ==<br />
The software is on the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. In what follows, we have added links to this website. To view these links you will need to login to the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. After following a link in this tutorial, you can click the back icon in your browser to get back to this tutorial (alternatively, if you '''right click''' you can open the link in a different window or tab). You can follow the instructions below in a separate window so that you can compare what you see in your working screen with the links and descriptions given in this tutorial.<br />
<br />
Also, please note that if you are using a customer specific installation of Sketch Engine, rather than the http://www.sketchengine.co.uk/ website, the appearance of your screen may be slightly different, for example with regard to the colour, logos or text formatting. <br />
<br />
If you are not a registered user yet, we recommend that you set up a free Sketch Engine trial account before reading on, so that you can look at the examples on the [https://trac.sketchengine.co.uk/wiki/Corpora/BNC BNC] referenced below. Where possible we also provide alternative links to the same examples on the open [http://acl-arc.comp.nus.edu.sg/ ACL Anthology Reference Corpus], which you can open without logging in. Note though that some of the text below relates specifically to the results on BNC and you will see different data and different numbers on ACL ARC.<br />
<br />
Follow the links from [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/] page to either set up an account, or log in. The "home" screen looks like this: [http://the.sketchengine.co.uk/auth/corpora/ click here].<br />
<br />
Wherever you are in Sketch Engine, the link back to this home page is always displayed at the top right hand corner. Likewise you can always see "Settings", which allows you to update personal information and your password, and the "Log out" link.<br />
<br />
On the left hand side, you see options for creating corpora and a few other tools.<br />
<br />
In the main panel you can select your corpus . Here we want to explore the British National Corpus, so we click on that.<br />
<br />
If you prefer to work with an open corpus, you can go to the [http://the.sketchengine.co.uk/open/ list of open corpora] and click on the ACL Anthology Reference Corpus.<br />
<br />
== Generating a concordance ==<br />
Your screen should then look like the link below:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/bnc2; click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/aclarc; click here (ACL ARC; no login required)]<br />
<br />
In the left hand side panel the option:<br />
* '''Concordance''' will always bring you back to this screen<br />
<br />
while:<br />
* '''Word List'''<br />
* '''Word Sketch'''<br />
* '''Thesaurus'''<br />
* '''Find X'''<br />
* '''Sketch-Diff'''<br />
<br />
take you to other tools which will be described in the sections below. <br />
<br />
To generate a concordance, you enter the main search term in the ([https://trac.sketchengine.co.uk/wiki/SkE/Help/SimpleQuery simple]) query box in the main panel of the screen.<br />
<br />
If, like the BNC, the corpus is lemmatized, the terms will match the lemma (the stemmed form) as well as the word. If you enter ''save'', the Sketch Engine will generate a concordance of all of the following:<br />
i) ''save-saved-saves-saving'' (verb)[[BR]]<br />
ii) ''save-save''s (noun - what goalkeepers make)[[BR]]<br />
iii) ''save'' (preposition: ''everyone was killed save Franco himself'')<br />
<br />
You can also enter phrases in the query box.<br />
<br />
To make more specific searches, you can select from the dropdown "Query Type" menu. This allows you to make specific types of queries:<br />
<br />
<br />
* simple: is the standard query which will match the lemma as well as the word as described above<br />
* lemma: will again match any lemma but here you can specify the part of speech (PoS i.e. the grammatical class e.g. noun, verb, adjective etc...). This option will not work for phrases. (Here and below we assume the corpus is, like the BNC, lemmatized and part-of-speech tagged. If it is not, not all of these query type options are available.)<br />
* phrase: will match a phrase e.g. ''runs away'', and any capitalised variant e.g. ''Runs away'', but will not match the lemma, so in this example ''run away'' will not be found.<br />
* Word form will match any word form exactly, you can select the PoS (e.g. noun or verb). You can also select whether you wish the system to match the exact capitisation you entered using "match case". For example, this will enable you to search for ''Bush'' rather than ''bush ''.<br />
* character matches a character string. For example, ''ate'' will match words containing this character sequence. This might be particularly useful in languages where tokenisation is difficult.<br />
* CQL: is for inputting complex queries using Corpus Query Language, described in [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying Corpus Querying and Grammar Writing]. "Default attribute" controls how CQL queries will be understood. The "tagset summary" box gives details of the part-of-speech tags used in the tagging. <br />
<br />
<br />
If you do not want to specify context any more precisely, you are now ready to hit the "Make Concordance" button and see the concordance. You will find more information about manipulating the output in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted#concres Section 4] below. Note that when you have obtained the concordance you can always get back to the query entry form described here by clicking on "Concordance" at the top of the left hand side panel. The next sections explain how to limit your search to a specific context or text type.<br />
<br />
For the purposes of reading the following context and text type sections, make sure you are at the concordance entry form (by clicking concordance at the top of the left hand side menu) select "lemma" as the query type in the concordance entry form. For future reference note that all the options from this section are available with all the options described in the following sections on context and text type.<br />
<br />
=== The Context section ===<br />
<br />
Now open the Context section by clicking on the "Context" expert option in the left hand side panel.<br />
<br />
With the Context option you can make various specifications on the lemmas and/or PoS in the words surrounding your query. For both the lemma and PoS constraints you can indicate whether the system should look for the lemmas (or PoS) to the left or right or at either side (both) of your query term. You also get a chance to specify how many tokens (words or punctuation), up to 15, of context to search for these constraints. You enter any number of lemmas or PoS and can specify if they should "all" apply, or whether "any" or "none" should be matched.<br />
<br />
Here are some examples:<br />
<br />
1. you want to search for the lemma ''shake'' (verb) followed by ''head'' (noun), to find instances such as ''she shook her head'', ''if you agree shake your head'', and ''shaking their heads in disbelief...'' You can do the following:<br />
* either type ''shake'' in the query box with PoS verb. Then type ''head'' in the Context lemma box PoS noun and specify Right and a window size (say 3 tokens)<br />
* or type ''head'' in the query box with PoS noun. Then type ''shake'' in the Context lemma box with PoS verb and specify Left and a window size (say 3 tokens)<br />
The results will be the same whichever route you take.<br />
<br />
2. you want to search for the verb ''taste'' followed by ''any'' adjective; since a following adjective may appear either in position 1 (''it tastes horrible''), position 2 (''it tastes really delicious''), or even position 3 (''it didn't taste quite so good''). Type ''taste'' in the query box, with query type lemma and PoS "verb". Then - in the Context area - select "adjective" from the PoS list and specify Right and a window size of 3 tokens. This generates a concordance of 480 lines in the BNC. You can further refine your search by specifying two PoS in the Context section. In this case, if you select both "adjective" and "adverb" by holding the CTRL key to select more than one PoS you will get a smaller concordance of 125 lines, with examples such as ''it tastes bloody awful'' and ''it tastes surprisingly good''. <br />
<br />
You can clear any boxes with the "clear all" option at the bottom of the screen.<br />
<br />
There are many more complex searches you can carry out using this feature - it is worth trying things out to see what is possible. For example, you could further refine the first search here (with ''head''=Lemma and ''shake''=Left Context ) by also specifying a PoS in the Right Context. Thus specifying "adverb" in the Right Context will generate lines such as ''shook his head '''disapprovingly''''', whereas specifying "noun" will generate ''shook their heads in '''agreement'''''. There are very many searches one might try, though in practice most searches are relatively simple.<br />
<br />
Context searches can also be used to exclude unwanted items: thus you could input a query of ''weapons of'' using the phrase option for the Query type (described in the section above), then exclude "destruction" by typing it into the Context Lemma box, specifying Right and then selecting "None" from the drop-down list. This returns a concordance for any lines containing the string ''weapons of'' ''without'' the word ''destruction''.<br />
<br />
<br />
=== The Text Type section ===<br />
Return to the concordance query form, if you are not already there, by clicking on "Concordance" at the top of the left hand side menu. Close the Context section by clicking on the expert option "Context" and select the option "Text Type", again, in the left hand side panel. <br />
<br />
With the '''Text Types''' option you can limit your search to a part of the corpus. If you want to see how a word behaves in the spoken part of the corpus, enter the word in the search box (or combine with other search specifications as described above) and tick the boxes for "Spoken context governed" and "Spoken demographic". Your concordance will contain only spoken-language examples. The partitions available depend on the text types (also referred to as header information or metadata) provided in the corpus data.<br />
<br />
== Manipulating your concordance output == <br />
Once you have generated a concordance, there are several options for increasing its usefulness. Click on "Concordance", chose a query type simple search and enter the word ''haunt'' and click "Make Concordance".<br />
<br />
<br />
The concordance screen looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Fbnc2&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Faclarc&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (ACL ARC; no login required)]<br />
<br />
As before, the options above the bar in the left hand side will take you to other parts of the program and are described below. The options below the horizontal bar in the left hand side menu allow you to work on this concordance. <br />
<br />
The panel directly above the concordance tells you which corpus you are using, and how many hits match your search item. For ''haunt'', there are 1098 concordance lines.<br />
<br />
=== Moving around the concordance ===<br />
You can move from one part of the concordance to another either by specifying a number in the '''Page''' box and selecting '''Go''', or by clicking on '''Next''', '''Last''', '''First''' or '''Previous'''.<br />
<br />
=== Finding out about a particular concordance line ===<br />
If you click on one of the highlighted node words, more of its context appears in the panel at the bottom of the screen and you can further expand the context by clicking on '''expand left''' and/or '''expand right'''. To hide this extra context click on the "-" in the top left hand of the context window.<br />
<br />
To get information about the source-text a particular concordance line comes from, click the document-id code at the left-hand end of the relevant line (assuming you have not changed the "View option" relating to "references", see below). This brings up "header" information in the bottom pane.<br />
<br />
=== The concordance menu ===<br />
<br />
In the lower section of the left hand side panel there are various options for refining your concordance. <br />
<br />
* '''View Options''': takes you to a new screen in the main panel that allows you to change the concordance view in various ways. To summarise the functions available when you select View Options (NB if you do click '''view options''' then you can select '''view concordance''' to get back) :<br />
* the '''Attributes''' column allows you to change from the default display (in which only the text is visible in the concordance line) to a number of alternative views in which you can see PoS-tags, lemmatized forms, and any other fields of information, either for the node word only ("KWIC tokens only") or for every word in the concordance line ("For each token"). The function can be useful for finding out why an unexpected corpus line has matched a query, as the cause is sometimes an incorrect PoS-tag or lemmatization <br />
* the '''Structures '''column allows you to change from the default display to show the beginning and end tags for structures such as sentences, paragraphs and documents. <br />
* the '''References''' column dictates the type of information regarding the source texts which appears (in blue) at the left-hand end of the concordance line. The default is an identifier for the document that the concordance line is taken from. Any other fields of information about corpus documents can be selected and the value that the concordance line has for that field will then be seen. For example, if the corpus encodes whether a document is imaginative writing or not, and the appropriate feature (e.g. in the BNC this is "Domain for written corpus texts") is selected in the References column and '''change view options''' is clicked, then the domain of the concordance lines will be displayed in the left hand column and we can see those that come from an "imaginative" text.<br />
* the '''Page Size''' box (bottom left) allows you to specify a longer page length for the display: the default is that each page of concordances contains 20 lines. (Increasing the Page Size will slow down initial retrieval of the concordance.) <br />
* '''KWIC Context size''' allows you to specify the size of the context window in number of characters<br />
* '''Sort good dictionary examples''' allows you to specify how many lines of 'good' examples that the system should automatically rank at the top of the concordance according to the GDEX program (see http://www.kilgarriff.co.uk/Publications/2008-KilgEtAl-euralex-gdex.doc)<br />
* '''Icon for one-click sentence copying''': You can add an icon for copying lines from the concordance <br />
* '''Allow multiple lines selection''' - Allow user to select and/or copy more than one line at once.<br />
* '''XML template for one-click copying''' (A feature used for specific projects only)<br />
<br />
* '''KWIC/Sentence''' lets you toggle between standard KWIC concordance view (which appears by default) and full sentence view.<br />
<br />
* '''Save''' gives you options for sorting the concordance. You can specify whether the output is text or xml, how many pages, whether a heading is included, whether the lines are numbered, whether the KWIC are aligned in the output and the maximum number of lines.<br />
<br />
* '''Sort''': Sorting is often a quick way of revealing patterns. If you select this option in the left hand side panel you obtain a screen in the main panel with various complex options for sorting (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sortconc the page specific help on Sort]) you can alternatively use the other options below '''sort''' to simply sort by:<br />
* '''Left:''' one token (word or punctuation) to the left<br />
* '''Right''': one token to the right<br />
* '''Node''': the KWIC (also referred to as the node word) <br />
* '''References''': sorting according to whichever references you display to the left of the concordance lines (as described in view options above).<br />
* '''Shuffle''': this shuffles the concordance so that the lines are arbitrarily ordered. Since the sample option described below always provides the same ordering for a give sized sample, this allows you to jumble the concordance so you can view only a portion of the concordance or your sample, without bias from the ordering.<br />
<br />
* '''Sample''': This allows you to create a random sample of the corpus lines. You can specify the size of the sample (i.e. the number of lines) or use the default of 250. For example, if you search for ''play'' (verb) and decide that you do not want to analyse 37,632 lines, use this option to reduce this to a manageable number. (see also [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sampleconc specific help on the random sample page])<br />
<br />
* '''Filter''': This allows you to specify constraints on the context of your KWIC to retrieve a subset of your concordance. See [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/filterconc the filter page specific help]<br />
<br />
* '''Frequency''' allows you to produce two types of frequency information regarding your search term:<br />
1. '''Multilevel frequency distribution''' shows the frequency of each form of a given lemma. To see how this works, make a concordance for ''forge'' (verb): when the concordance displays, select '''Frequency''' and use the '''Multilevel frequency distribution''' section. The (default) "first level" shows you the frequencies of the forms ''forge'', ''forged'', ''forging'' and ''forges''. The second and third levels allow more complex searches of this type: for example if you check "second level" and select "1R" (=word one position to right of node word) you will see which words appear in this position and how frequent each of these words is. <br />
2. '''Text type frequency distribution''' shows how your search term is distributed through the texts in the corpus. You may find, for example, that a word like ''police'' appears significantly more often in newspaper texts than in other text types. This is a potentially useful tool which could show you - for example - that a particular medical term is not restricted to specialised medical discourse. As with the "references" column in the "View Options" screen, the actual values you can select depend on the corpus you are using, and how it has been set up in the Sketch Engine. <br />
* The frequency option is also described in [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/freqconc the page specific help on frequency]. You can alternatively use the simpler frequency options below '''Frequency''' to simply sort by:<br />
* '''Node tags''': the PoS tags for all the KWIC word forms (node word types)<br />
* '''Node forms''': the word forms for all the KWIC word forms<br />
* '''Doc IDs''': frequency distribution over the document ids<br />
* '''Text Types''': frequency distribution over all the text types specified for the corpus<br />
<br />
* '''Collocations''' allows you to generate lists of words that co-occur frequently with your node word (its "collocates"). Where word sketches (see the next section) are available, they give a more sophisticated account of collocates in most cases. (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/collocconc collocations page specific help])<br />
<br />
* '''Original Concordance''': is visible if you have refined your concordance. If you select this you can get rid of the refinements and return to the original concordance.<br />
<br />
* '''!ConcDesc''': provides a technical description of your query. This is useful for programmers and technical people.<br />
<br />
== The Word Sketch function == <br />
<br />
A Word Sketch is a corpus-based summary of a word's grammatical and collocational behaviour. <br />
<br />
Click on '''Word Sketch''' in the left hand side main menu (top section of the left hand side menu), and this takes you to the Word Sketch entry form, which looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/bnc2;lemma=;lpos= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/aclarc;lemma=;lpos= click here (ACL ARC; no login required)]<br />
<br />
Choose a lemma and specify its part of speech using the drop-down list. Word Sketches are typically available for nouns, verbs, and adjectives and can be available for other word classes depending on the grammatical definitions supplied to the sketch engine (see [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying#wordsketchdefs the documentation on grammatical relation definitions] for more information). Word sketches also depend on the availability of substantial amounts of data, so if you try to create a Word Sketch for a fairly rare item you will see a message saying there is no Word Sketch available. (This is perfectly reasonable: the point of the Word Sketches is to provide helpful summaries when there is too much corpus data to scan efficiently using a concordance; but when there are only a few concordance lines it is easy enough to analyse them all manually.) In general, you need several hundred instances of a word to make a useful word sketch.<br />
<br />
This [http://bit.ly/JrYY5i link] shows a Word Sketch for the noun ''challenge''. ([http://bit.ly/JrYxbd Alternative link] for ACL ARC.)<br />
<br />
Each column show the words that typically combine with ''challenge'' in a particular grammatical relations (or "gramrels"). Most of these gramrels are self-explanatory. For example, "object_of" lists - in order of statistical significance rather than raw frequency - the verbs that most typically occupy the verb slot in cases where ''challenge'' is the object of a verb. Most of the data is lexicographically relevant, though one might query the adjectival modifier ''larval'': it turns out that ''larval challenge'' is a technical term used in parasitology, discussed in a BNC document.<br />
<br />
You can at any time switch between Concordance mode and Word Sketch mode, and this is a useful way of getting more information about a particular word combination. Thus, if you want to look at examples of "''pose'' + ''challenge''" (where ''challenge'' is the direct object of ''pose''), simply click on the number next to ''pose'' in the "object_of" list ('''92''') and you will be taken directly to a concordance showing all instances of this combination.<br />
<br />
== The Thesaurus function == <br />
The software checks to see which words occur with the same collocates as other words, and on the basis of this data it generates a "distributional thesaurus". A distributional thesaurus is an automatically produced "thesaurus" which finds words that tend to occur in similar contexts as the target word. It is '''not''' a man made thesaurus of synonyms. The thesaurus function lists, for any given adjective, noun or verb, the other words ''most similar'' to it in in terms of grammatical and collocational behaviour.<br />
<br />
Click on the '''Thesaurus''' link on the left hand side main (top) menu and then input the word with PoS that you are interested in. <br />
<br />
For help on the advanced options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/Thesaurus the thesaurus help page].<br />
<br />
== The Sketch Difference function == <br />
Sketch Difference is a neat way of comparing two very similar words: it shows those patterns and combinations that the two items have in common, and also those patterns and combinations that are more typical of, or unique to, one word rather than the other. You can also use the function to compare the same lemma in two different parts of the corpus, or to compare two different word forms e.g. ''men'' and ''man''. Click on any word in a Thesaurus entry for a word, and you will be taken straight to a screen showing the Sketch Difference between the two words. Alternatively, you can click on '''Sketch-Diff''' on the left hand side panel and this will take you to the word sketch difference entry form which gives you more options.<br />
<br />
Suppose you want to compare ''clever '' and ''intelligent''. In the thesaurus entry for ''clever'', ''intelligent '' comes top of the list: it is statistically the most similar word in terms of shared contexts of occurrence. Click on ''intelligent'' and you are taken to a new screen which is in three main parts: the first part shows "Common Patterns" (those combinations where ''clever'' and ''intelligent'' behave quite similarly), the second and third parts show "clever only patterns" and "intelligent only patterns". The screen looks like this [http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Fbnc2&lemma=clever&lpos=-j&usesubcorp=;lemma2=intelligent click here]. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Faclarc&lemma=clever&lpos=-j&diff_by=lemma&lemma2=intelligent Alternative link] for ACL ARC.) <br />
<br />
In the "Common Patterns" part, there are four numbers next to each collocate. The first two indicate the frequency of co-occurrence with the first and second lemma, the last two show the salience scores for the collocate with both lemmas. All collocates are sorted according to maximum of the two salience scores and coloured according to difference between the scores.<br />
<br />
Try this out, and look at the difference in the "and/or" lists: people can be "intelligent and articulate/thoughtful/sensitive" etc, but they are often "clever and devious/cunning/brave". <br />
<br />
For more information on the other options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/SketchDiff the Word Sketch Difference help]<br />
<br />
== The Search function ==<br />
<br />
From any screen you can do a "simple" '''Search''' in any corpus by using the field and drop down list in the horizontal panel which appears just beneath the very top bar in which you can search the Help documentation. This search function provides a short cut to a simple concordance<br />
<br />
== Other functions ==<br />
<br />
For an explanation of other functions in the left hand side margin you can click the help links marked with a '''?'''<br />
<br />
----<br />
Click [https://trac.sketchengine.co.uk/wiki/WikiStart here] for the Start Page for Sketch Engine Documentation.</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Sketch_Engine&diff=9338Sketch Engine2012-05-11T18:18:58Z<p>Sivareddy: </p>
<hr />
<div>== Background ==<br />
The Sketch Engine is a web-based program which takes as its input a corpus of any language with an appropriate level of linguistic mark-up. The Sketch Engine has a number of language-analysis functions, the core ones being:<br />
* '''the Concordancer''' A program which displays all occurrences from the corpus for a given query. The program is very powerful with a wide variety of query types and many different ways of displaying and organising the results.<br />
* '''the Word Sketch program''' This program provides a corpus-based summary of a word's grammatical and collocational behaviour. It will be described below in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted/#wordsketchid section 5].<br />
<br />
For the purposes of this guide, we use examples based on the Sketch Engine loaded with a sample corpus of English, the British National Corpus (BNC). For more information about the Sketch Engine, see [https://trac.sketchengine.co.uk/wiki/SkE/DocsIndex:sketch-engine-elx04.pdf Kilgarriff et al 2004 in Proc EURALEX]. For more information about the BNC, see [http://www.natcorp.ox.ac.uk/ http://www.natcorp.ox.ac.uk/]. <br />
<br />
<br />
Most terminology is defined as it is encountered below, however for a full glossary please see our [https://trac.sketchengine.co.uk/wiki/SkE/Help/JargonBuster Jargon Buster]<br />
<br />
<br />
== Home page ==<br />
The software is on the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. In what follows, we have added links to this website. To view these links you will need to login to the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. After following a link in this tutorial, you can click the back icon in your browser to get back to this tutorial (alternatively, if you '''right click''' you can open the link in a different window or tab). You can follow the instructions below in a separate window so that you can compare what you see in your working screen with the links and descriptions given in this tutorial.<br />
<br />
Also, please note that if you are using a customer specific installation of Sketch Engine, rather than the http://www.sketchengine.co.uk/ website, the appearance of your screen may be slightly different, for example with regard to the colour, logos or text formatting. <br />
<br />
If you are not a registered user yet, we recommend that you set up a free Sketch Engine trial account before reading on, so that you can look at the examples on the [https://trac.sketchengine.co.uk/wiki/Corpora/BNC BNC] referenced below. Where possible we also provide alternative links to the same examples on the open [http://acl-arc.comp.nus.edu.sg/ ACL Anthology Reference Corpus], which you can open without logging in. Note though that some of the text below relates specifically to the results on BNC and you will see different data and different numbers on ACL ARC.<br />
<br />
Follow the links from [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/] page to either set up an account, or log in. The "home" screen looks like this: [http://the.sketchengine.co.uk/auth/corpora/ click here].<br />
<br />
Wherever you are in Sketch Engine, the link back to this home page is always displayed at the top right hand corner. Likewise you can always see "Settings", which allows you to update personal information and your password, and the "Log out" link.<br />
<br />
On the left hand side, you see options for creating corpora and a few other tools.<br />
<br />
In the main panel you can select your corpus . Here we want to explore the British National Corpus, so we click on that.<br />
<br />
If you prefer to work with an open corpus, you can go to the [http://the.sketchengine.co.uk/open/ list of open corpora] and click on the ACL Anthology Reference Corpus.<br />
<br />
== Generating a concordance ==<br />
Your screen should then look like the link below:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/bnc2; click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/aclarc; click here (ACL ARC; no login required)]<br />
<br />
In the left hand side panel the option:<br />
* '''Concordance''' will always bring you back to this screen<br />
<br />
while:<br />
* '''Word List'''<br />
* '''Word Sketch'''<br />
* '''Thesaurus'''<br />
* '''Find X'''<br />
* '''Sketch-Diff'''<br />
<br />
take you to other tools which will be described in the sections below. <br />
<br />
To generate a concordance, you enter the main search term in the ([https://trac.sketchengine.co.uk/wiki/SkE/Help/SimpleQuery simple]) query box in the main panel of the screen.<br />
<br />
If, like the BNC, the corpus is lemmatized, the terms will match the lemma (the stemmed form) as well as the word. If you enter ''save'', the Sketch Engine will generate a concordance of all of the following:<br />
i) ''save-saved-saves-saving'' (verb)[[BR]]<br />
ii) ''save-save''s (noun - what goalkeepers make)[[BR]]<br />
iii) ''save'' (preposition: ''everyone was killed save Franco himself'')<br />
<br />
You can also enter phrases in the query box.<br />
<br />
To make more specific searches, you can select from the dropdown "Query Type" menu. This allows you to make specific types of queries:<br />
<br />
<br />
* simple: is the standard query which will match the lemma as well as the word as described above<br />
* lemma: will again match any lemma but here you can specify the part of speech (PoS i.e. the grammatical class e.g. noun, verb, adjective etc...). This option will not work for phrases. (Here and below we assume the corpus is, like the BNC, lemmatized and part-of-speech tagged. If it is not, not all of these query type options are available.)<br />
* phrase: will match a phrase e.g. ''runs away'', and any capitalised variant e.g. ''Runs away'', but will not match the lemma, so in this example ''run away'' will not be found.<br />
* Word form will match any word form exactly, you can select the PoS (e.g. noun or verb). You can also select whether you wish the system to match the exact capitisation you entered using "match case". For example, this will enable you to search for ''Bush'' rather than ''bush ''.<br />
* character matches a character string. For example, ''ate'' will match words containing this character sequence. This might be particularly useful in languages where tokenisation is difficult.<br />
* CQL: is for inputting complex queries using Corpus Query Language, described in [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying Corpus Querying and Grammar Writing]. "Default attribute" controls how CQL queries will be understood. The "tagset summary" box gives details of the part-of-speech tags used in the tagging. <br />
<br />
<br />
If you do not want to specify context any more precisely, you are now ready to hit the "Make Concordance" button and see the concordance. You will find more information about manipulating the output in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted#concres Section 4] below. Note that when you have obtained the concordance you can always get back to the query entry form described here by clicking on "Concordance" at the top of the left hand side panel. The next sections explain how to limit your search to a specific context or text type.<br />
<br />
For the purposes of reading the following context and text type sections, make sure you are at the concordance entry form (by clicking concordance at the top of the left hand side menu) select "lemma" as the query type in the concordance entry form. For future reference note that all the options from this section are available with all the options described in the following sections on context and text type.<br />
<br />
=== The Context section ===<br />
<br />
Now open the Context section by clicking on the "Context" expert option in the left hand side panel.<br />
<br />
With the Context option you can make various specifications on the lemmas and/or PoS in the words surrounding your query. For both the lemma and PoS constraints you can indicate whether the system should look for the lemmas (or PoS) to the left or right or at either side (both) of your query term. You also get a chance to specify how many tokens (words or punctuation), up to 15, of context to search for these constraints. You enter any number of lemmas or PoS and can specify if they should "all" apply, or whether "any" or "none" should be matched.<br />
<br />
Here are some examples:<br />
<br />
1. you want to search for the lemma ''shake'' (verb) followed by ''head'' (noun), to find instances such as ''she shook her head'', ''if you agree shake your head'', and ''shaking their heads in disbelief...'' You can do the following:<br />
* either type ''shake'' in the query box with PoS verb. Then type ''head'' in the Context lemma box PoS noun and specify Right and a window size (say 3 tokens)<br />
* or type ''head'' in the query box with PoS noun. Then type ''shake'' in the Context lemma box with PoS verb and specify Left and a window size (say 3 tokens)<br />
The results will be the same whichever route you take.<br />
<br />
2. you want to search for the verb ''taste'' followed by ''any'' adjective; since a following adjective may appear either in position 1 (''it tastes horrible''), position 2 (''it tastes really delicious''), or even position 3 (''it didn't taste quite so good''). Type ''taste'' in the query box, with query type lemma and PoS "verb". Then - in the Context area - select "adjective" from the PoS list and specify Right and a window size of 3 tokens. This generates a concordance of 480 lines in the BNC. You can further refine your search by specifying two PoS in the Context section. In this case, if you select both "adjective" and "adverb" by holding the CTRL key to select more than one PoS you will get a smaller concordance of 125 lines, with examples such as ''it tastes bloody awful'' and ''it tastes surprisingly good''. <br />
<br />
You can clear any boxes with the "clear all" option at the bottom of the screen.<br />
<br />
There are many more complex searches you can carry out using this feature - it is worth trying things out to see what is possible. For example, you could further refine the first search here (with ''head''=Lemma and ''shake''=Left Context ) by also specifying a PoS in the Right Context. Thus specifying "adverb" in the Right Context will generate lines such as ''shook his head '''disapprovingly''''', whereas specifying "noun" will generate ''shook their heads in '''agreement'''''. There are very many searches one might try, though in practice most searches are relatively simple.<br />
<br />
Context searches can also be used to exclude unwanted items: thus you could input a query of ''weapons of'' using the phrase option for the Query type (described in the section above), then exclude "destruction" by typing it into the Context Lemma box, specifying Right and then selecting "None" from the drop-down list. This returns a concordance for any lines containing the string ''weapons of'' ''without'' the word ''destruction''.<br />
<br />
<br />
=== The Text Type section ===<br />
Return to the concordance query form, if you are not already there, by clicking on "Concordance" at the top of the left hand side menu. Close the Context section by clicking on the expert option "Context" and select the option "Text Type", again, in the left hand side panel. <br />
<br />
With the '''Text Types''' option you can limit your search to a part of the corpus. If you want to see how a word behaves in the spoken part of the corpus, enter the word in the search box (or combine with other search specifications as described above) and tick the boxes for "Spoken context governed" and "Spoken demographic". Your concordance will contain only spoken-language examples. The partitions available depend on the text types (also referred to as header information or metadata) provided in the corpus data.<br />
<br />
== Manipulating your concordance output == #concres<br />
Once you have generated a concordance, there are several options for increasing its usefulness. Click on "Concordance", chose a query type simple search and enter the word ''haunt'' and click "Make Concordance".<br />
<br />
<br />
The concordance screen looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Fbnc2&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Faclarc&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (ACL ARC; no login required)]<br />
<br />
As before, the options above the bar in the left hand side will take you to other parts of the program and are described below. The options below the horizontal bar in the left hand side menu allow you to work on this concordance. <br />
<br />
The panel directly above the concordance tells you which corpus you are using, and how many hits match your search item. For ''haunt'', there are 1098 concordance lines.<br />
<br />
=== Moving around the concordance ===<br />
You can move from one part of the concordance to another either by specifying a number in the '''Page''' box and selecting '''Go''', or by clicking on '''Next''', '''Last''', '''First''' or '''Previous'''.<br />
<br />
=== Finding out about a particular concordance line ===<br />
If you click on one of the highlighted node words, more of its context appears in the panel at the bottom of the screen and you can further expand the context by clicking on '''expand left''' and/or '''expand right'''. To hide this extra context click on the "-" in the top left hand of the context window.<br />
<br />
To get information about the source-text a particular concordance line comes from, click the document-id code at the left-hand end of the relevant line (assuming you have not changed the "View option" relating to "references", see below). This brings up "header" information in the bottom pane.<br />
<br />
=== The concordance menu ===#concmenu<br />
<br />
In the lower section of the left hand side panel there are various options for refining your concordance. <br />
<br />
* '''View Options''': takes you to a new screen in the main panel that allows you to change the concordance view in various ways. To summarise the functions available when you select View Options (NB if you do click '''view options''' then you can select '''view concordance''' to get back) :<br />
* the '''Attributes''' column allows you to change from the default display (in which only the text is visible in the concordance line) to a number of alternative views in which you can see PoS-tags, lemmatized forms, and any other fields of information, either for the node word only ("KWIC tokens only") or for every word in the concordance line ("For each token"). The function can be useful for finding out why an unexpected corpus line has matched a query, as the cause is sometimes an incorrect PoS-tag or lemmatization <br />
* the '''Structures '''column allows you to change from the default display to show the beginning and end tags for structures such as sentences, paragraphs and documents. <br />
* the '''References''' column dictates the type of information regarding the source texts which appears (in blue) at the left-hand end of the concordance line. The default is an identifier for the document that the concordance line is taken from. Any other fields of information about corpus documents can be selected and the value that the concordance line has for that field will then be seen. For example, if the corpus encodes whether a document is imaginative writing or not, and the appropriate feature (e.g. in the BNC this is "Domain for written corpus texts") is selected in the References column and '''change view options''' is clicked, then the domain of the concordance lines will be displayed in the left hand column and we can see those that come from an "imaginative" text.<br />
* the '''Page Size''' box (bottom left) allows you to specify a longer page length for the display: the default is that each page of concordances contains 20 lines. (Increasing the Page Size will slow down initial retrieval of the concordance.) <br />
* '''KWIC Context size''' allows you to specify the size of the context window in number of characters<br />
* '''Sort good dictionary examples''' allows you to specify how many lines of 'good' examples that the system should automatically rank at the top of the concordance according to the GDEX program (see http://www.kilgarriff.co.uk/Publications/2008-KilgEtAl-euralex-gdex.doc)<br />
* '''Icon for one-click sentence copying''': You can add an icon for copying lines from the concordance <br />
* '''Allow multiple lines selection''' - Allow user to select and/or copy more than one line at once.<br />
* '''XML template for one-click copying''' (A feature used for specific projects only)<br />
<br />
* '''KWIC/Sentence''' lets you toggle between standard KWIC concordance view (which appears by default) and full sentence view.<br />
<br />
* '''Save''' gives you options for sorting the concordance. You can specify whether the output is text or xml, how many pages, whether a heading is included, whether the lines are numbered, whether the KWIC are aligned in the output and the maximum number of lines.<br />
<br />
* '''Sort''': Sorting is often a quick way of revealing patterns. If you select this option in the left hand side panel you obtain a screen in the main panel with various complex options for sorting (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sortconc the page specific help on Sort]) you can alternatively use the other options below '''sort''' to simply sort by:<br />
* '''Left:''' one token (word or punctuation) to the left<br />
* '''Right''': one token to the right<br />
* '''Node''': the KWIC (also referred to as the node word) <br />
* '''References''': sorting according to whichever references you display to the left of the concordance lines (as described in view options above).<br />
* '''Shuffle''': this shuffles the concordance so that the lines are arbitrarily ordered. Since the sample option described below always provides the same ordering for a give sized sample, this allows you to jumble the concordance so you can view only a portion of the concordance or your sample, without bias from the ordering.<br />
<br />
* '''Sample''': This allows you to create a random sample of the corpus lines. You can specify the size of the sample (i.e. the number of lines) or use the default of 250. For example, if you search for ''play'' (verb) and decide that you do not want to analyse 37,632 lines, use this option to reduce this to a manageable number. (see also [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sampleconc specific help on the random sample page])<br />
<br />
* '''Filter''': This allows you to specify constraints on the context of your KWIC to retrieve a subset of your concordance. See [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/filterconc the filter page specific help]<br />
<br />
* '''Frequency''' allows you to produce two types of frequency information regarding your search term:<br />
1. '''Multilevel frequency distribution''' shows the frequency of each form of a given lemma. To see how this works, make a concordance for ''forge'' (verb): when the concordance displays, select '''Frequency''' and use the '''Multilevel frequency distribution''' section. The (default) "first level" shows you the frequencies of the forms ''forge'', ''forged'', ''forging'' and ''forges''. The second and third levels allow more complex searches of this type: for example if you check "second level" and select "1R" (=word one position to right of node word) you will see which words appear in this position and how frequent each of these words is. <br />
2. '''Text type frequency distribution''' shows how your search term is distributed through the texts in the corpus. You may find, for example, that a word like ''police'' appears significantly more often in newspaper texts than in other text types. This is a potentially useful tool which could show you - for example - that a particular medical term is not restricted to specialised medical discourse. As with the "references" column in the "View Options" screen, the actual values you can select depend on the corpus you are using, and how it has been set up in the Sketch Engine. <br />
* The frequency option is also described in [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/freqconc the page specific help on frequency]. You can alternatively use the simpler frequency options below '''Frequency''' to simply sort by:<br />
* '''Node tags''': the PoS tags for all the KWIC word forms (node word types)<br />
* '''Node forms''': the word forms for all the KWIC word forms<br />
* '''Doc IDs''': frequency distribution over the document ids<br />
* '''Text Types''': frequency distribution over all the text types specified for the corpus<br />
<br />
* '''Collocations''' allows you to generate lists of words that co-occur frequently with your node word (its "collocates"). Where word sketches (see the next section) are available, they give a more sophisticated account of collocates in most cases. (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/collocconc collocations page specific help])<br />
<br />
* '''Original Concordance''': is visible if you have refined your concordance. If you select this you can get rid of the refinements and return to the original concordance.<br />
<br />
* '''!ConcDesc''': provides a technical description of your query. This is useful for programmers and technical people.<br />
<br />
== The Word Sketch function == <br />
<br />
A Word Sketch is a corpus-based summary of a word's grammatical and collocational behaviour. <br />
<br />
Click on '''Word Sketch''' in the left hand side main menu (top section of the left hand side menu), and this takes you to the Word Sketch entry form, which looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/bnc2;lemma=;lpos= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/aclarc;lemma=;lpos= click here (ACL ARC; no login required)]<br />
<br />
Choose a lemma and specify its part of speech using the drop-down list. Word Sketches are typically available for nouns, verbs, and adjectives and can be available for other word classes depending on the grammatical definitions supplied to the sketch engine (see [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying#wordsketchdefs the documentation on grammatical relation definitions] for more information). Word sketches also depend on the availability of substantial amounts of data, so if you try to create a Word Sketch for a fairly rare item you will see a message saying there is no Word Sketch available. (This is perfectly reasonable: the point of the Word Sketches is to provide helpful summaries when there is too much corpus data to scan efficiently using a concordance; but when there are only a few concordance lines it is easy enough to analyse them all manually.) In general, you need several hundred instances of a word to make a useful word sketch.<br />
<br />
This [http://bit.ly/JrYY5i link] shows a Word Sketch for the noun ''challenge''. ([http://bit.ly/JrYxbd Alternative link] for ACL ARC.)<br />
<br />
Each column show the words that typically combine with ''challenge'' in a particular grammatical relations (or "gramrels"). Most of these gramrels are self-explanatory. For example, "object_of" lists - in order of statistical significance rather than raw frequency - the verbs that most typically occupy the verb slot in cases where ''challenge'' is the object of a verb. Most of the data is lexicographically relevant, though one might query the adjectival modifier ''larval'': it turns out that ''larval challenge'' is a technical term used in parasitology, discussed in a BNC document.<br />
<br />
You can at any time switch between Concordance mode and Word Sketch mode, and this is a useful way of getting more information about a particular word combination. Thus, if you want to look at examples of "''pose'' + ''challenge''" (where ''challenge'' is the direct object of ''pose''), simply click on the number next to ''pose'' in the "object_of" list ('''92''') and you will be taken directly to a concordance showing all instances of this combination.<br />
<br />
== The Thesaurus function == <br />
The software checks to see which words occur with the same collocates as other words, and on the basis of this data it generates a "distributional thesaurus". A distributional thesaurus is an automatically produced "thesaurus" which finds words that tend to occur in similar contexts as the target word. It is '''not''' a man made thesaurus of synonyms. The thesaurus function lists, for any given adjective, noun or verb, the other words ''most similar'' to it in in terms of grammatical and collocational behaviour.<br />
<br />
Click on the '''Thesaurus''' link on the left hand side main (top) menu and then input the word with PoS that you are interested in. <br />
<br />
For help on the advanced options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/Thesaurus the thesaurus help page].<br />
<br />
== The Sketch Difference function == <br />
Sketch Difference is a neat way of comparing two very similar words: it shows those patterns and combinations that the two items have in common, and also those patterns and combinations that are more typical of, or unique to, one word rather than the other. You can also use the function to compare the same lemma in two different parts of the corpus, or to compare two different word forms e.g. ''men'' and ''man''. Click on any word in a Thesaurus entry for a word, and you will be taken straight to a screen showing the Sketch Difference between the two words. Alternatively, you can click on '''Sketch-Diff''' on the left hand side panel and this will take you to the word sketch difference entry form which gives you more options.<br />
<br />
Suppose you want to compare ''clever '' and ''intelligent''. In the thesaurus entry for ''clever'', ''intelligent '' comes top of the list: it is statistically the most similar word in terms of shared contexts of occurrence. Click on ''intelligent'' and you are taken to a new screen which is in three main parts: the first part shows "Common Patterns" (those combinations where ''clever'' and ''intelligent'' behave quite similarly), the second and third parts show "clever only patterns" and "intelligent only patterns". The screen looks like this [http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Fbnc2&lemma=clever&lpos=-j&usesubcorp=;lemma2=intelligent click here]. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Faclarc&lemma=clever&lpos=-j&diff_by=lemma&lemma2=intelligent Alternative link] for ACL ARC.) <br />
<br />
In the "Common Patterns" part, there are four numbers next to each collocate. The first two indicate the frequency of co-occurrence with the first and second lemma, the last two show the salience scores for the collocate with both lemmas. All collocates are sorted according to maximum of the two salience scores and coloured according to difference between the scores.<br />
<br />
Try this out, and look at the difference in the "and/or" lists: people can be "intelligent and articulate/thoughtful/sensitive" etc, but they are often "clever and devious/cunning/brave". <br />
<br />
For more information on the other options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/SketchDiff the Word Sketch Difference help]<br />
<br />
== The Search function ==<br />
<br />
From any screen you can do a "simple" '''Search''' in any corpus by using the field and drop down list in the horizontal panel which appears just beneath the very top bar in which you can search the Help documentation. This search function provides a short cut to a simple concordance<br />
<br />
== Other functions ==<br />
<br />
For an explanation of other functions in the left hand side margin you can click the help links marked with a '''?'''<br />
<br />
----<br />
Click [https://trac.sketchengine.co.uk/wiki/WikiStart here] for the Start Page for Sketch Engine Documentation.</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Sketch_Engine&diff=9337Sketch Engine2012-05-11T18:17:29Z<p>Sivareddy: </p>
<hr />
<div>== 1. Background ==<br />
The Sketch Engine is a web-based program which takes as its input a corpus of any language with an appropriate level of linguistic mark-up. The Sketch Engine has a number of language-analysis functions, the core ones being:<br />
* '''the Concordancer''' A program which displays all occurrences from the corpus for a given query. The program is very powerful with a wide variety of query types and many different ways of displaying and organising the results.<br />
* '''the Word Sketch program''' This program provides a corpus-based summary of a word's grammatical and collocational behaviour. It will be described below in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted/#wordsketchid section 5].<br />
<br />
For the purposes of this guide, we use examples based on the Sketch Engine loaded with a sample corpus of English, the British National Corpus (BNC). For more information about the Sketch Engine, see [https://trac.sketchengine.co.uk/wiki/SkE/DocsIndex:sketch-engine-elx04.pdf Kilgarriff et al 2004 in Proc EURALEX]. For more information about the BNC, see [http://www.natcorp.ox.ac.uk/ http://www.natcorp.ox.ac.uk/]. <br />
<br />
<br />
Most terminology is defined as it is encountered below, however for a full glossary please see our [https://trac.sketchengine.co.uk/wiki/SkE/Help/JargonBuster Jargon Buster]<br />
<br />
<br />
== 2. Home page ==<br />
The software is on the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. In what follows, we have added links to this website. To view these links you will need to login to the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. After following a link in this tutorial, you can click the back icon in your browser to get back to this tutorial (alternatively, if you '''right click''' you can open the link in a different window or tab). You can follow the instructions below in a separate window so that you can compare what you see in your working screen with the links and descriptions given in this tutorial.<br />
<br />
Also, please note that if you are using a customer specific installation of Sketch Engine, rather than the http://www.sketchengine.co.uk/ website, the appearance of your screen may be slightly different, for example with regard to the colour, logos or text formatting. <br />
<br />
If you are not a registered user yet, we recommend that you set up a free Sketch Engine trial account before reading on, so that you can look at the examples on the [https://trac.sketchengine.co.uk/wiki/Corpora/BNC BNC] referenced below. Where possible we also provide alternative links to the same examples on the open [http://acl-arc.comp.nus.edu.sg/ ACL Anthology Reference Corpus], which you can open without logging in. Note though that some of the text below relates specifically to the results on BNC and you will see different data and different numbers on ACL ARC.<br />
<br />
Follow the links from [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/] page to either set up an account, or log in. The "home" screen looks like this: [http://the.sketchengine.co.uk/auth/corpora/ click here].<br />
<br />
Wherever you are in Sketch Engine, the link back to this home page is always displayed at the top right hand corner. Likewise you can always see "Settings", which allows you to update personal information and your password, and the "Log out" link.<br />
<br />
On the left hand side, you see options for creating corpora and a few other tools.<br />
<br />
In the main panel you can select your corpus . Here we want to explore the British National Corpus, so we click on that.<br />
<br />
If you prefer to work with an open corpus, you can go to the [http://the.sketchengine.co.uk/open/ list of open corpora] and click on the ACL Anthology Reference Corpus.<br />
<br />
== 3. Generating a concordance ==<br />
Your screen should then look like the link below:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/bnc2; click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/aclarc; click here (ACL ARC; no login required)]<br />
<br />
In the left hand side panel the option:<br />
* '''Concordance''' will always bring you back to this screen<br />
<br />
while:<br />
* '''Word List'''<br />
* '''Word Sketch'''<br />
* '''Thesaurus'''<br />
* '''Find X'''<br />
* '''Sketch-Diff'''<br />
<br />
take you to other tools which will be described in the sections below. <br />
<br />
To generate a concordance, you enter the main search term in the ([https://trac.sketchengine.co.uk/wiki/SkE/Help/SimpleQuery simple]) query box in the main panel of the screen.<br />
<br />
If, like the BNC, the corpus is lemmatized, the terms will match the lemma (the stemmed form) as well as the word. If you enter ''save'', the Sketch Engine will generate a concordance of all of the following:<br />
i) ''save-saved-saves-saving'' (verb)[[BR]]<br />
ii) ''save-save''s (noun - what goalkeepers make)[[BR]]<br />
iii) ''save'' (preposition: ''everyone was killed save Franco himself'')<br />
<br />
You can also enter phrases in the query box.<br />
<br />
To make more specific searches, you can select from the dropdown "Query Type" menu. This allows you to make specific types of queries:<br />
<br />
<br />
* simple: is the standard query which will match the lemma as well as the word as described above<br />
* lemma: will again match any lemma but here you can specify the part of speech (PoS i.e. the grammatical class e.g. noun, verb, adjective etc...). This option will not work for phrases. (Here and below we assume the corpus is, like the BNC, lemmatized and part-of-speech tagged. If it is not, not all of these query type options are available.)<br />
* phrase: will match a phrase e.g. ''runs away'', and any capitalised variant e.g. ''Runs away'', but will not match the lemma, so in this example ''run away'' will not be found.<br />
* Word form will match any word form exactly, you can select the PoS (e.g. noun or verb). You can also select whether you wish the system to match the exact capitisation you entered using "match case". For example, this will enable you to search for ''Bush'' rather than ''bush ''.<br />
* character matches a character string. For example, ''ate'' will match words containing this character sequence. This might be particularly useful in languages where tokenisation is difficult.<br />
* CQL: is for inputting complex queries using Corpus Query Language, described in [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying Corpus Querying and Grammar Writing]. "Default attribute" controls how CQL queries will be understood. The "tagset summary" box gives details of the part-of-speech tags used in the tagging. <br />
<br />
<br />
If you do not want to specify context any more precisely, you are now ready to hit the "Make Concordance" button and see the concordance. You will find more information about manipulating the output in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted#concres Section 4] below. Note that when you have obtained the concordance you can always get back to the query entry form described here by clicking on "Concordance" at the top of the left hand side panel. The next sections explain how to limit your search to a specific context or text type.<br />
<br />
For the purposes of reading the following context and text type sections, make sure you are at the concordance entry form (by clicking concordance at the top of the left hand side menu) select "lemma" as the query type in the concordance entry form. For future reference note that all the options from this section are available with all the options described in the following sections on context and text type.<br />
<br />
=== The Context section ===<br />
<br />
Now open the Context section by clicking on the "Context" expert option in the left hand side panel.<br />
<br />
With the Context option you can make various specifications on the lemmas and/or PoS in the words surrounding your query. For both the lemma and PoS constraints you can indicate whether the system should look for the lemmas (or PoS) to the left or right or at either side (both) of your query term. You also get a chance to specify how many tokens (words or punctuation), up to 15, of context to search for these constraints. You enter any number of lemmas or PoS and can specify if they should "all" apply, or whether "any" or "none" should be matched.<br />
<br />
Here are some examples:<br />
<br />
1. you want to search for the lemma ''shake'' (verb) followed by ''head'' (noun), to find instances such as ''she shook her head'', ''if you agree shake your head'', and ''shaking their heads in disbelief...'' You can do the following:<br />
* either type ''shake'' in the query box with PoS verb. Then type ''head'' in the Context lemma box PoS noun and specify Right and a window size (say 3 tokens)<br />
* or type ''head'' in the query box with PoS noun. Then type ''shake'' in the Context lemma box with PoS verb and specify Left and a window size (say 3 tokens)<br />
The results will be the same whichever route you take.<br />
<br />
2. you want to search for the verb ''taste'' followed by ''any'' adjective; since a following adjective may appear either in position 1 (''it tastes horrible''), position 2 (''it tastes really delicious''), or even position 3 (''it didn't taste quite so good''). Type ''taste'' in the query box, with query type lemma and PoS "verb". Then - in the Context area - select "adjective" from the PoS list and specify Right and a window size of 3 tokens. This generates a concordance of 480 lines in the BNC. You can further refine your search by specifying two PoS in the Context section. In this case, if you select both "adjective" and "adverb" by holding the CTRL key to select more than one PoS you will get a smaller concordance of 125 lines, with examples such as ''it tastes bloody awful'' and ''it tastes surprisingly good''. <br />
<br />
You can clear any boxes with the "clear all" option at the bottom of the screen.<br />
<br />
There are many more complex searches you can carry out using this feature - it is worth trying things out to see what is possible. For example, you could further refine the first search here (with ''head''=Lemma and ''shake''=Left Context ) by also specifying a PoS in the Right Context. Thus specifying "adverb" in the Right Context will generate lines such as ''shook his head '''disapprovingly''''', whereas specifying "noun" will generate ''shook their heads in '''agreement'''''. There are very many searches one might try, though in practice most searches are relatively simple.<br />
<br />
Context searches can also be used to exclude unwanted items: thus you could input a query of ''weapons of'' using the phrase option for the Query type (described in the section above), then exclude "destruction" by typing it into the Context Lemma box, specifying Right and then selecting "None" from the drop-down list. This returns a concordance for any lines containing the string ''weapons of'' ''without'' the word ''destruction''.<br />
<br />
<br />
=== The Text Type section ===<br />
Return to the concordance query form, if you are not already there, by clicking on "Concordance" at the top of the left hand side menu. Close the Context section by clicking on the expert option "Context" and select the option "Text Type", again, in the left hand side panel. <br />
<br />
With the '''Text Types''' option you can limit your search to a part of the corpus. If you want to see how a word behaves in the spoken part of the corpus, enter the word in the search box (or combine with other search specifications as described above) and tick the boxes for "Spoken context governed" and "Spoken demographic". Your concordance will contain only spoken-language examples. The partitions available depend on the text types (also referred to as header information or metadata) provided in the corpus data.<br />
<br />
== 4. Manipulating your concordance output == #concres<br />
Once you have generated a concordance, there are several options for increasing its usefulness. Click on "Concordance", chose a query type simple search and enter the word ''haunt'' and click "Make Concordance".<br />
<br />
<br />
The concordance screen looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Fbnc2&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Faclarc&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (ACL ARC; no login required)]<br />
<br />
As before, the options above the bar in the left hand side will take you to other parts of the program and are described below. The options below the horizontal bar in the left hand side menu allow you to work on this concordance. <br />
<br />
The panel directly above the concordance tells you which corpus you are using, and how many hits match your search item. For ''haunt'', there are 1098 concordance lines.<br />
<br />
=== Moving around the concordance ===<br />
You can move from one part of the concordance to another either by specifying a number in the '''Page''' box and selecting '''Go''', or by clicking on '''Next''', '''Last''', '''First''' or '''Previous'''.<br />
<br />
=== Finding out about a particular concordance line ===<br />
If you click on one of the highlighted node words, more of its context appears in the panel at the bottom of the screen and you can further expand the context by clicking on '''expand left''' and/or '''expand right'''. To hide this extra context click on the "-" in the top left hand of the context window.<br />
<br />
To get information about the source-text a particular concordance line comes from, click the document-id code at the left-hand end of the relevant line (assuming you have not changed the "View option" relating to "references", see below). This brings up "header" information in the bottom pane.<br />
<br />
=== The concordance menu ===#concmenu<br />
<br />
In the lower section of the left hand side panel there are various options for refining your concordance. <br />
<br />
* '''View Options''': takes you to a new screen in the main panel that allows you to change the concordance view in various ways. To summarise the functions available when you select View Options (NB if you do click '''view options''' then you can select '''view concordance''' to get back) :<br />
* the '''Attributes''' column allows you to change from the default display (in which only the text is visible in the concordance line) to a number of alternative views in which you can see PoS-tags, lemmatized forms, and any other fields of information, either for the node word only ("KWIC tokens only") or for every word in the concordance line ("For each token"). The function can be useful for finding out why an unexpected corpus line has matched a query, as the cause is sometimes an incorrect PoS-tag or lemmatization <br />
* the '''Structures '''column allows you to change from the default display to show the beginning and end tags for structures such as sentences, paragraphs and documents. <br />
* the '''References''' column dictates the type of information regarding the source texts which appears (in blue) at the left-hand end of the concordance line. The default is an identifier for the document that the concordance line is taken from. Any other fields of information about corpus documents can be selected and the value that the concordance line has for that field will then be seen. For example, if the corpus encodes whether a document is imaginative writing or not, and the appropriate feature (e.g. in the BNC this is "Domain for written corpus texts") is selected in the References column and '''change view options''' is clicked, then the domain of the concordance lines will be displayed in the left hand column and we can see those that come from an "imaginative" text.<br />
* the '''Page Size''' box (bottom left) allows you to specify a longer page length for the display: the default is that each page of concordances contains 20 lines. (Increasing the Page Size will slow down initial retrieval of the concordance.) <br />
* '''KWIC Context size''' allows you to specify the size of the context window in number of characters<br />
* '''Sort good dictionary examples''' allows you to specify how many lines of 'good' examples that the system should automatically rank at the top of the concordance according to the GDEX program (see http://www.kilgarriff.co.uk/Publications/2008-KilgEtAl-euralex-gdex.doc)<br />
* '''Icon for one-click sentence copying''': You can add an icon for copying lines from the concordance <br />
* '''Allow multiple lines selection''' - Allow user to select and/or copy more than one line at once.<br />
* '''XML template for one-click copying''' (A feature used for specific projects only)<br />
<br />
* '''KWIC/Sentence''' lets you toggle between standard KWIC concordance view (which appears by default) and full sentence view.<br />
<br />
* '''Save''' gives you options for sorting the concordance. You can specify whether the output is text or xml, how many pages, whether a heading is included, whether the lines are numbered, whether the KWIC are aligned in the output and the maximum number of lines.<br />
<br />
* '''Sort''': Sorting is often a quick way of revealing patterns. If you select this option in the left hand side panel you obtain a screen in the main panel with various complex options for sorting (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sortconc the page specific help on Sort]) you can alternatively use the other options below '''sort''' to simply sort by:<br />
* '''Left:''' one token (word or punctuation) to the left<br />
* '''Right''': one token to the right<br />
* '''Node''': the KWIC (also referred to as the node word) <br />
* '''References''': sorting according to whichever references you display to the left of the concordance lines (as described in view options above).<br />
* '''Shuffle''': this shuffles the concordance so that the lines are arbitrarily ordered. Since the sample option described below always provides the same ordering for a give sized sample, this allows you to jumble the concordance so you can view only a portion of the concordance or your sample, without bias from the ordering.<br />
<br />
* '''Sample''': This allows you to create a random sample of the corpus lines. You can specify the size of the sample (i.e. the number of lines) or use the default of 250. For example, if you search for ''play'' (verb) and decide that you do not want to analyse 37,632 lines, use this option to reduce this to a manageable number. (see also [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sampleconc specific help on the random sample page])<br />
<br />
* '''Filter''': This allows you to specify constraints on the context of your KWIC to retrieve a subset of your concordance. See [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/filterconc the filter page specific help]<br />
<br />
* '''Frequency''' allows you to produce two types of frequency information regarding your search term:<br />
1. '''Multilevel frequency distribution''' shows the frequency of each form of a given lemma. To see how this works, make a concordance for ''forge'' (verb): when the concordance displays, select '''Frequency''' and use the '''Multilevel frequency distribution''' section. The (default) "first level" shows you the frequencies of the forms ''forge'', ''forged'', ''forging'' and ''forges''. The second and third levels allow more complex searches of this type: for example if you check "second level" and select "1R" (=word one position to right of node word) you will see which words appear in this position and how frequent each of these words is. <br />
2. '''Text type frequency distribution''' shows how your search term is distributed through the texts in the corpus. You may find, for example, that a word like ''police'' appears significantly more often in newspaper texts than in other text types. This is a potentially useful tool which could show you - for example - that a particular medical term is not restricted to specialised medical discourse. As with the "references" column in the "View Options" screen, the actual values you can select depend on the corpus you are using, and how it has been set up in the Sketch Engine. <br />
* The frequency option is also described in [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/freqconc the page specific help on frequency]. You can alternatively use the simpler frequency options below '''Frequency''' to simply sort by:<br />
* '''Node tags''': the PoS tags for all the KWIC word forms (node word types)<br />
* '''Node forms''': the word forms for all the KWIC word forms<br />
* '''Doc IDs''': frequency distribution over the document ids<br />
* '''Text Types''': frequency distribution over all the text types specified for the corpus<br />
<br />
* '''Collocations''' allows you to generate lists of words that co-occur frequently with your node word (its "collocates"). Where word sketches (see the next section) are available, they give a more sophisticated account of collocates in most cases. (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/collocconc collocations page specific help])<br />
<br />
* '''Original Concordance''': is visible if you have refined your concordance. If you select this you can get rid of the refinements and return to the original concordance.<br />
<br />
* '''!ConcDesc''': provides a technical description of your query. This is useful for programmers and technical people.<br />
<br />
== 5. The Word Sketch function == <br />
<br />
A Word Sketch is a corpus-based summary of a word's grammatical and collocational behaviour. <br />
<br />
Click on '''Word Sketch''' in the left hand side main menu (top section of the left hand side menu), and this takes you to the Word Sketch entry form, which looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/bnc2;lemma=;lpos= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/aclarc;lemma=;lpos= click here (ACL ARC; no login required)]<br />
<br />
Choose a lemma and specify its part of speech using the drop-down list. Word Sketches are typically available for nouns, verbs, and adjectives and can be available for other word classes depending on the grammatical definitions supplied to the sketch engine (see [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying#wordsketchdefs the documentation on grammatical relation definitions] for more information). Word sketches also depend on the availability of substantial amounts of data, so if you try to create a Word Sketch for a fairly rare item you will see a message saying there is no Word Sketch available. (This is perfectly reasonable: the point of the Word Sketches is to provide helpful summaries when there is too much corpus data to scan efficiently using a concordance; but when there are only a few concordance lines it is easy enough to analyse them all manually.) In general, you need several hundred instances of a word to make a useful word sketch.<br />
<br />
This [http://bit.ly/JrYY5i link] shows a Word Sketch for the noun ''challenge''. ([http://bit.ly/JrYxbd Alternative link] for ACL ARC.)<br />
<br />
Each column show the words that typically combine with ''challenge'' in a particular grammatical relations (or "gramrels"). Most of these gramrels are self-explanatory. For example, "object_of" lists - in order of statistical significance rather than raw frequency - the verbs that most typically occupy the verb slot in cases where ''challenge'' is the object of a verb. Most of the data is lexicographically relevant, though one might query the adjectival modifier ''larval'': it turns out that ''larval challenge'' is a technical term used in parasitology, discussed in a BNC document.<br />
<br />
You can at any time switch between Concordance mode and Word Sketch mode, and this is a useful way of getting more information about a particular word combination. Thus, if you want to look at examples of "''pose'' + ''challenge''" (where ''challenge'' is the direct object of ''pose''), simply click on the number next to ''pose'' in the "object_of" list ('''92''') and you will be taken directly to a concordance showing all instances of this combination.<br />
<br />
== 6. The Thesaurus function == <br />
The software checks to see which words occur with the same collocates as other words, and on the basis of this data it generates a "distributional thesaurus". A distributional thesaurus is an automatically produced "thesaurus" which finds words that tend to occur in similar contexts as the target word. It is '''not''' a man made thesaurus of synonyms. The thesaurus function lists, for any given adjective, noun or verb, the other words ''most similar'' to it in in terms of grammatical and collocational behaviour.<br />
<br />
Click on the '''Thesaurus''' link on the left hand side main (top) menu and then input the word with PoS that you are interested in. <br />
<br />
For help on the advanced options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/Thesaurus the thesaurus help page].<br />
<br />
== 7. The Sketch Difference function == <br />
Sketch Difference is a neat way of comparing two very similar words: it shows those patterns and combinations that the two items have in common, and also those patterns and combinations that are more typical of, or unique to, one word rather than the other. You can also use the function to compare the same lemma in two different parts of the corpus, or to compare two different word forms e.g. ''men'' and ''man''. Click on any word in a Thesaurus entry for a word, and you will be taken straight to a screen showing the Sketch Difference between the two words. Alternatively, you can click on '''Sketch-Diff''' on the left hand side panel and this will take you to the word sketch difference entry form which gives you more options.<br />
<br />
Suppose you want to compare ''clever '' and ''intelligent''. In the thesaurus entry for ''clever'', ''intelligent '' comes top of the list: it is statistically the most similar word in terms of shared contexts of occurrence. Click on ''intelligent'' and you are taken to a new screen which is in three main parts: the first part shows "Common Patterns" (those combinations where ''clever'' and ''intelligent'' behave quite similarly), the second and third parts show "clever only patterns" and "intelligent only patterns". The screen looks like this [http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Fbnc2&lemma=clever&lpos=-j&usesubcorp=;lemma2=intelligent click here]. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Faclarc&lemma=clever&lpos=-j&diff_by=lemma&lemma2=intelligent Alternative link] for ACL ARC.) <br />
<br />
In the "Common Patterns" part, there are four numbers next to each collocate. The first two indicate the frequency of co-occurrence with the first and second lemma, the last two show the salience scores for the collocate with both lemmas. All collocates are sorted according to maximum of the two salience scores and coloured according to difference between the scores.<br />
<br />
Try this out, and look at the difference in the "and/or" lists: people can be "intelligent and articulate/thoughtful/sensitive" etc, but they are often "clever and devious/cunning/brave". <br />
<br />
For more information on the other options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/SketchDiff the Word Sketch Difference help]<br />
<br />
== 8. The Search function ==<br />
<br />
From any screen you can do a "simple" '''Search''' in any corpus by using the field and drop down list in the horizontal panel which appears just beneath the very top bar in which you can search the Help documentation. This search function provides a short cut to a simple concordance<br />
<br />
== 9. Other functions ==<br />
<br />
For an explanation of other functions in the left hand side margin you can click the help links marked with a '''?'''<br />
<br />
----<br />
Click [https://trac.sketchengine.co.uk/wiki/WikiStart here] for the Start Page for Sketch Engine Documentation.</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Sketch_Engine&diff=9336Sketch Engine2012-05-11T18:16:58Z<p>Sivareddy: </p>
<hr />
<div>= Sketch Engine =<br />
<br />
== 1. Background ==<br />
The Sketch Engine is a web-based program which takes as its input a corpus of any language with an appropriate level of linguistic mark-up. The Sketch Engine has a number of language-analysis functions, the core ones being:<br />
* '''the Concordancer''' A program which displays all occurrences from the corpus for a given query. The program is very powerful with a wide variety of query types and many different ways of displaying and organising the results.<br />
* '''the Word Sketch program''' This program provides a corpus-based summary of a word's grammatical and collocational behaviour. It will be described below in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted/#wordsketchid section 5].<br />
<br />
For the purposes of this guide, we use examples based on the Sketch Engine loaded with a sample corpus of English, the British National Corpus (BNC). For more information about the Sketch Engine, see [https://trac.sketchengine.co.uk/wiki/SkE/DocsIndex:sketch-engine-elx04.pdf Kilgarriff et al 2004 in Proc EURALEX]. For more information about the BNC, see [http://www.natcorp.ox.ac.uk/ http://www.natcorp.ox.ac.uk/]. <br />
<br />
<br />
Most terminology is defined as it is encountered below, however for a full glossary please see our [https://trac.sketchengine.co.uk/wiki/SkE/Help/JargonBuster Jargon Buster]<br />
<br />
<br />
== 2. Home page ==<br />
The software is on the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. In what follows, we have added links to this website. To view these links you will need to login to the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. After following a link in this tutorial, you can click the back icon in your browser to get back to this tutorial (alternatively, if you '''right click''' you can open the link in a different window or tab). You can follow the instructions below in a separate window so that you can compare what you see in your working screen with the links and descriptions given in this tutorial.<br />
<br />
Also, please note that if you are using a customer specific installation of Sketch Engine, rather than the http://www.sketchengine.co.uk/ website, the appearance of your screen may be slightly different, for example with regard to the colour, logos or text formatting. <br />
<br />
If you are not a registered user yet, we recommend that you set up a free Sketch Engine trial account before reading on, so that you can look at the examples on the [https://trac.sketchengine.co.uk/wiki/Corpora/BNC BNC] referenced below. Where possible we also provide alternative links to the same examples on the open [http://acl-arc.comp.nus.edu.sg/ ACL Anthology Reference Corpus], which you can open without logging in. Note though that some of the text below relates specifically to the results on BNC and you will see different data and different numbers on ACL ARC.<br />
<br />
Follow the links from [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/] page to either set up an account, or log in. The "home" screen looks like this: [http://the.sketchengine.co.uk/auth/corpora/ click here].<br />
<br />
Wherever you are in Sketch Engine, the link back to this home page is always displayed at the top right hand corner. Likewise you can always see "Settings", which allows you to update personal information and your password, and the "Log out" link.<br />
<br />
On the left hand side, you see options for creating corpora and a few other tools.<br />
<br />
In the main panel you can select your corpus . Here we want to explore the British National Corpus, so we click on that.<br />
<br />
If you prefer to work with an open corpus, you can go to the [http://the.sketchengine.co.uk/open/ list of open corpora] and click on the ACL Anthology Reference Corpus.<br />
<br />
== 3. Generating a concordance ==<br />
Your screen should then look like the link below:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/bnc2; click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/aclarc; click here (ACL ARC; no login required)]<br />
<br />
In the left hand side panel the option:<br />
* '''Concordance''' will always bring you back to this screen<br />
<br />
while:<br />
* '''Word List'''<br />
* '''Word Sketch'''<br />
* '''Thesaurus'''<br />
* '''Find X'''<br />
* '''Sketch-Diff'''<br />
<br />
take you to other tools which will be described in the sections below. <br />
<br />
To generate a concordance, you enter the main search term in the ([https://trac.sketchengine.co.uk/wiki/SkE/Help/SimpleQuery simple]) query box in the main panel of the screen.<br />
<br />
If, like the BNC, the corpus is lemmatized, the terms will match the lemma (the stemmed form) as well as the word. If you enter ''save'', the Sketch Engine will generate a concordance of all of the following:<br />
i) ''save-saved-saves-saving'' (verb)[[BR]]<br />
ii) ''save-save''s (noun - what goalkeepers make)[[BR]]<br />
iii) ''save'' (preposition: ''everyone was killed save Franco himself'')<br />
<br />
You can also enter phrases in the query box.<br />
<br />
To make more specific searches, you can select from the dropdown "Query Type" menu. This allows you to make specific types of queries:<br />
<br />
<br />
* simple: is the standard query which will match the lemma as well as the word as described above<br />
* lemma: will again match any lemma but here you can specify the part of speech (PoS i.e. the grammatical class e.g. noun, verb, adjective etc...). This option will not work for phrases. (Here and below we assume the corpus is, like the BNC, lemmatized and part-of-speech tagged. If it is not, not all of these query type options are available.)<br />
* phrase: will match a phrase e.g. ''runs away'', and any capitalised variant e.g. ''Runs away'', but will not match the lemma, so in this example ''run away'' will not be found.<br />
* Word form will match any word form exactly, you can select the PoS (e.g. noun or verb). You can also select whether you wish the system to match the exact capitisation you entered using "match case". For example, this will enable you to search for ''Bush'' rather than ''bush ''.<br />
* character matches a character string. For example, ''ate'' will match words containing this character sequence. This might be particularly useful in languages where tokenisation is difficult.<br />
* CQL: is for inputting complex queries using Corpus Query Language, described in [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying Corpus Querying and Grammar Writing]. "Default attribute" controls how CQL queries will be understood. The "tagset summary" box gives details of the part-of-speech tags used in the tagging. <br />
<br />
<br />
If you do not want to specify context any more precisely, you are now ready to hit the "Make Concordance" button and see the concordance. You will find more information about manipulating the output in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted#concres Section 4] below. Note that when you have obtained the concordance you can always get back to the query entry form described here by clicking on "Concordance" at the top of the left hand side panel. The next sections explain how to limit your search to a specific context or text type.<br />
<br />
For the purposes of reading the following context and text type sections, make sure you are at the concordance entry form (by clicking concordance at the top of the left hand side menu) select "lemma" as the query type in the concordance entry form. For future reference note that all the options from this section are available with all the options described in the following sections on context and text type.<br />
<br />
=== The Context section ===<br />
<br />
Now open the Context section by clicking on the "Context" expert option in the left hand side panel.<br />
<br />
With the Context option you can make various specifications on the lemmas and/or PoS in the words surrounding your query. For both the lemma and PoS constraints you can indicate whether the system should look for the lemmas (or PoS) to the left or right or at either side (both) of your query term. You also get a chance to specify how many tokens (words or punctuation), up to 15, of context to search for these constraints. You enter any number of lemmas or PoS and can specify if they should "all" apply, or whether "any" or "none" should be matched.<br />
<br />
Here are some examples:<br />
<br />
1. you want to search for the lemma ''shake'' (verb) followed by ''head'' (noun), to find instances such as ''she shook her head'', ''if you agree shake your head'', and ''shaking their heads in disbelief...'' You can do the following:<br />
* either type ''shake'' in the query box with PoS verb. Then type ''head'' in the Context lemma box PoS noun and specify Right and a window size (say 3 tokens)<br />
* or type ''head'' in the query box with PoS noun. Then type ''shake'' in the Context lemma box with PoS verb and specify Left and a window size (say 3 tokens)<br />
The results will be the same whichever route you take.<br />
<br />
2. you want to search for the verb ''taste'' followed by ''any'' adjective; since a following adjective may appear either in position 1 (''it tastes horrible''), position 2 (''it tastes really delicious''), or even position 3 (''it didn't taste quite so good''). Type ''taste'' in the query box, with query type lemma and PoS "verb". Then - in the Context area - select "adjective" from the PoS list and specify Right and a window size of 3 tokens. This generates a concordance of 480 lines in the BNC. You can further refine your search by specifying two PoS in the Context section. In this case, if you select both "adjective" and "adverb" by holding the CTRL key to select more than one PoS you will get a smaller concordance of 125 lines, with examples such as ''it tastes bloody awful'' and ''it tastes surprisingly good''. <br />
<br />
You can clear any boxes with the "clear all" option at the bottom of the screen.<br />
<br />
There are many more complex searches you can carry out using this feature - it is worth trying things out to see what is possible. For example, you could further refine the first search here (with ''head''=Lemma and ''shake''=Left Context ) by also specifying a PoS in the Right Context. Thus specifying "adverb" in the Right Context will generate lines such as ''shook his head '''disapprovingly''''', whereas specifying "noun" will generate ''shook their heads in '''agreement'''''. There are very many searches one might try, though in practice most searches are relatively simple.<br />
<br />
Context searches can also be used to exclude unwanted items: thus you could input a query of ''weapons of'' using the phrase option for the Query type (described in the section above), then exclude "destruction" by typing it into the Context Lemma box, specifying Right and then selecting "None" from the drop-down list. This returns a concordance for any lines containing the string ''weapons of'' ''without'' the word ''destruction''.<br />
<br />
<br />
=== The Text Type section ===<br />
Return to the concordance query form, if you are not already there, by clicking on "Concordance" at the top of the left hand side menu. Close the Context section by clicking on the expert option "Context" and select the option "Text Type", again, in the left hand side panel. <br />
<br />
With the '''Text Types''' option you can limit your search to a part of the corpus. If you want to see how a word behaves in the spoken part of the corpus, enter the word in the search box (or combine with other search specifications as described above) and tick the boxes for "Spoken context governed" and "Spoken demographic". Your concordance will contain only spoken-language examples. The partitions available depend on the text types (also referred to as header information or metadata) provided in the corpus data.<br />
<br />
== 4. Manipulating your concordance output == #concres<br />
Once you have generated a concordance, there are several options for increasing its usefulness. Click on "Concordance", chose a query type simple search and enter the word ''haunt'' and click "Make Concordance".<br />
<br />
<br />
The concordance screen looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Fbnc2&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Faclarc&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (ACL ARC; no login required)]<br />
<br />
As before, the options above the bar in the left hand side will take you to other parts of the program and are described below. The options below the horizontal bar in the left hand side menu allow you to work on this concordance. <br />
<br />
The panel directly above the concordance tells you which corpus you are using, and how many hits match your search item. For ''haunt'', there are 1098 concordance lines.<br />
<br />
=== Moving around the concordance ===<br />
You can move from one part of the concordance to another either by specifying a number in the '''Page''' box and selecting '''Go''', or by clicking on '''Next''', '''Last''', '''First''' or '''Previous'''.<br />
<br />
=== Finding out about a particular concordance line ===<br />
If you click on one of the highlighted node words, more of its context appears in the panel at the bottom of the screen and you can further expand the context by clicking on '''expand left''' and/or '''expand right'''. To hide this extra context click on the "-" in the top left hand of the context window.<br />
<br />
To get information about the source-text a particular concordance line comes from, click the document-id code at the left-hand end of the relevant line (assuming you have not changed the "View option" relating to "references", see below). This brings up "header" information in the bottom pane.<br />
<br />
=== The concordance menu ===#concmenu<br />
<br />
In the lower section of the left hand side panel there are various options for refining your concordance. <br />
<br />
* '''View Options''': takes you to a new screen in the main panel that allows you to change the concordance view in various ways. To summarise the functions available when you select View Options (NB if you do click '''view options''' then you can select '''view concordance''' to get back) :<br />
* the '''Attributes''' column allows you to change from the default display (in which only the text is visible in the concordance line) to a number of alternative views in which you can see PoS-tags, lemmatized forms, and any other fields of information, either for the node word only ("KWIC tokens only") or for every word in the concordance line ("For each token"). The function can be useful for finding out why an unexpected corpus line has matched a query, as the cause is sometimes an incorrect PoS-tag or lemmatization <br />
* the '''Structures '''column allows you to change from the default display to show the beginning and end tags for structures such as sentences, paragraphs and documents. <br />
* the '''References''' column dictates the type of information regarding the source texts which appears (in blue) at the left-hand end of the concordance line. The default is an identifier for the document that the concordance line is taken from. Any other fields of information about corpus documents can be selected and the value that the concordance line has for that field will then be seen. For example, if the corpus encodes whether a document is imaginative writing or not, and the appropriate feature (e.g. in the BNC this is "Domain for written corpus texts") is selected in the References column and '''change view options''' is clicked, then the domain of the concordance lines will be displayed in the left hand column and we can see those that come from an "imaginative" text.<br />
* the '''Page Size''' box (bottom left) allows you to specify a longer page length for the display: the default is that each page of concordances contains 20 lines. (Increasing the Page Size will slow down initial retrieval of the concordance.) <br />
* '''KWIC Context size''' allows you to specify the size of the context window in number of characters<br />
* '''Sort good dictionary examples''' allows you to specify how many lines of 'good' examples that the system should automatically rank at the top of the concordance according to the GDEX program (see http://www.kilgarriff.co.uk/Publications/2008-KilgEtAl-euralex-gdex.doc)<br />
* '''Icon for one-click sentence copying''': You can add an icon for copying lines from the concordance <br />
* '''Allow multiple lines selection''' - Allow user to select and/or copy more than one line at once.<br />
* '''XML template for one-click copying''' (A feature used for specific projects only)<br />
<br />
* '''KWIC/Sentence''' lets you toggle between standard KWIC concordance view (which appears by default) and full sentence view.<br />
<br />
* '''Save''' gives you options for sorting the concordance. You can specify whether the output is text or xml, how many pages, whether a heading is included, whether the lines are numbered, whether the KWIC are aligned in the output and the maximum number of lines.<br />
<br />
* '''Sort''': Sorting is often a quick way of revealing patterns. If you select this option in the left hand side panel you obtain a screen in the main panel with various complex options for sorting (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sortconc the page specific help on Sort]) you can alternatively use the other options below '''sort''' to simply sort by:<br />
* '''Left:''' one token (word or punctuation) to the left<br />
* '''Right''': one token to the right<br />
* '''Node''': the KWIC (also referred to as the node word) <br />
* '''References''': sorting according to whichever references you display to the left of the concordance lines (as described in view options above).<br />
* '''Shuffle''': this shuffles the concordance so that the lines are arbitrarily ordered. Since the sample option described below always provides the same ordering for a give sized sample, this allows you to jumble the concordance so you can view only a portion of the concordance or your sample, without bias from the ordering.<br />
<br />
* '''Sample''': This allows you to create a random sample of the corpus lines. You can specify the size of the sample (i.e. the number of lines) or use the default of 250. For example, if you search for ''play'' (verb) and decide that you do not want to analyse 37,632 lines, use this option to reduce this to a manageable number. (see also [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sampleconc specific help on the random sample page])<br />
<br />
* '''Filter''': This allows you to specify constraints on the context of your KWIC to retrieve a subset of your concordance. See [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/filterconc the filter page specific help]<br />
<br />
* '''Frequency''' allows you to produce two types of frequency information regarding your search term:<br />
1. '''Multilevel frequency distribution''' shows the frequency of each form of a given lemma. To see how this works, make a concordance for ''forge'' (verb): when the concordance displays, select '''Frequency''' and use the '''Multilevel frequency distribution''' section. The (default) "first level" shows you the frequencies of the forms ''forge'', ''forged'', ''forging'' and ''forges''. The second and third levels allow more complex searches of this type: for example if you check "second level" and select "1R" (=word one position to right of node word) you will see which words appear in this position and how frequent each of these words is. <br />
2. '''Text type frequency distribution''' shows how your search term is distributed through the texts in the corpus. You may find, for example, that a word like ''police'' appears significantly more often in newspaper texts than in other text types. This is a potentially useful tool which could show you - for example - that a particular medical term is not restricted to specialised medical discourse. As with the "references" column in the "View Options" screen, the actual values you can select depend on the corpus you are using, and how it has been set up in the Sketch Engine. <br />
* The frequency option is also described in [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/freqconc the page specific help on frequency]. You can alternatively use the simpler frequency options below '''Frequency''' to simply sort by:<br />
* '''Node tags''': the PoS tags for all the KWIC word forms (node word types)<br />
* '''Node forms''': the word forms for all the KWIC word forms<br />
* '''Doc IDs''': frequency distribution over the document ids<br />
* '''Text Types''': frequency distribution over all the text types specified for the corpus<br />
<br />
* '''Collocations''' allows you to generate lists of words that co-occur frequently with your node word (its "collocates"). Where word sketches (see the next section) are available, they give a more sophisticated account of collocates in most cases. (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/collocconc collocations page specific help])<br />
<br />
* '''Original Concordance''': is visible if you have refined your concordance. If you select this you can get rid of the refinements and return to the original concordance.<br />
<br />
* '''!ConcDesc''': provides a technical description of your query. This is useful for programmers and technical people.<br />
<br />
== 5. The Word Sketch function == <br />
<br />
A Word Sketch is a corpus-based summary of a word's grammatical and collocational behaviour. <br />
<br />
Click on '''Word Sketch''' in the left hand side main menu (top section of the left hand side menu), and this takes you to the Word Sketch entry form, which looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/bnc2;lemma=;lpos= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/aclarc;lemma=;lpos= click here (ACL ARC; no login required)]<br />
<br />
Choose a lemma and specify its part of speech using the drop-down list. Word Sketches are typically available for nouns, verbs, and adjectives and can be available for other word classes depending on the grammatical definitions supplied to the sketch engine (see [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying#wordsketchdefs the documentation on grammatical relation definitions] for more information). Word sketches also depend on the availability of substantial amounts of data, so if you try to create a Word Sketch for a fairly rare item you will see a message saying there is no Word Sketch available. (This is perfectly reasonable: the point of the Word Sketches is to provide helpful summaries when there is too much corpus data to scan efficiently using a concordance; but when there are only a few concordance lines it is easy enough to analyse them all manually.) In general, you need several hundred instances of a word to make a useful word sketch.<br />
<br />
This [http://bit.ly/JrYY5i link] shows a Word Sketch for the noun ''challenge''. ([http://bit.ly/JrYxbd Alternative link] for ACL ARC.)<br />
<br />
Each column show the words that typically combine with ''challenge'' in a particular grammatical relations (or "gramrels"). Most of these gramrels are self-explanatory. For example, "object_of" lists - in order of statistical significance rather than raw frequency - the verbs that most typically occupy the verb slot in cases where ''challenge'' is the object of a verb. Most of the data is lexicographically relevant, though one might query the adjectival modifier ''larval'': it turns out that ''larval challenge'' is a technical term used in parasitology, discussed in a BNC document.<br />
<br />
You can at any time switch between Concordance mode and Word Sketch mode, and this is a useful way of getting more information about a particular word combination. Thus, if you want to look at examples of "''pose'' + ''challenge''" (where ''challenge'' is the direct object of ''pose''), simply click on the number next to ''pose'' in the "object_of" list ('''92''') and you will be taken directly to a concordance showing all instances of this combination.<br />
<br />
== 6. The Thesaurus function == <br />
The software checks to see which words occur with the same collocates as other words, and on the basis of this data it generates a "distributional thesaurus". A distributional thesaurus is an automatically produced "thesaurus" which finds words that tend to occur in similar contexts as the target word. It is '''not''' a man made thesaurus of synonyms. The thesaurus function lists, for any given adjective, noun or verb, the other words ''most similar'' to it in in terms of grammatical and collocational behaviour.<br />
<br />
Click on the '''Thesaurus''' link on the left hand side main (top) menu and then input the word with PoS that you are interested in. <br />
<br />
For help on the advanced options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/Thesaurus the thesaurus help page].<br />
<br />
== 7. The Sketch Difference function == <br />
Sketch Difference is a neat way of comparing two very similar words: it shows those patterns and combinations that the two items have in common, and also those patterns and combinations that are more typical of, or unique to, one word rather than the other. You can also use the function to compare the same lemma in two different parts of the corpus, or to compare two different word forms e.g. ''men'' and ''man''. Click on any word in a Thesaurus entry for a word, and you will be taken straight to a screen showing the Sketch Difference between the two words. Alternatively, you can click on '''Sketch-Diff''' on the left hand side panel and this will take you to the word sketch difference entry form which gives you more options.<br />
<br />
Suppose you want to compare ''clever '' and ''intelligent''. In the thesaurus entry for ''clever'', ''intelligent '' comes top of the list: it is statistically the most similar word in terms of shared contexts of occurrence. Click on ''intelligent'' and you are taken to a new screen which is in three main parts: the first part shows "Common Patterns" (those combinations where ''clever'' and ''intelligent'' behave quite similarly), the second and third parts show "clever only patterns" and "intelligent only patterns". The screen looks like this [http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Fbnc2&lemma=clever&lpos=-j&usesubcorp=;lemma2=intelligent click here]. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Faclarc&lemma=clever&lpos=-j&diff_by=lemma&lemma2=intelligent Alternative link] for ACL ARC.) <br />
<br />
In the "Common Patterns" part, there are four numbers next to each collocate. The first two indicate the frequency of co-occurrence with the first and second lemma, the last two show the salience scores for the collocate with both lemmas. All collocates are sorted according to maximum of the two salience scores and coloured according to difference between the scores.<br />
<br />
Try this out, and look at the difference in the "and/or" lists: people can be "intelligent and articulate/thoughtful/sensitive" etc, but they are often "clever and devious/cunning/brave". <br />
<br />
For more information on the other options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/SketchDiff the Word Sketch Difference help]<br />
<br />
== 8. The Search function ==<br />
<br />
From any screen you can do a "simple" '''Search''' in any corpus by using the field and drop down list in the horizontal panel which appears just beneath the very top bar in which you can search the Help documentation. This search function provides a short cut to a simple concordance<br />
<br />
== 9. Other functions ==<br />
<br />
For an explanation of other functions in the left hand side margin you can click the help links marked with a '''?'''<br />
<br />
----<br />
Click [https://trac.sketchengine.co.uk/wiki/WikiStart here] for the Start Page for Sketch Engine Documentation.</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=User:Sivareddy&diff=9335User:Sivareddy2012-05-11T18:09:40Z<p>Sivareddy: </p>
<hr />
<div>Name: Siva Reddy<br />
<br />
Webpage: http://sivareddy.in<br />
<br />
CV: http://sivareddy.in/cv_siva.pdf<br />
<br />
Research Interests: Lexical Semantics, Semantic Composition, Multiwords, Machine Learning, Word Sense Disambiguation/Induction, Lexical Acquisition, Web Corpora, Web as a Resource for NLP problems, Cross Language Resources, Syntactic Parsing, Question Answering Inference<br />
<br />
Keywords: [[Polysemy]], [[Compositionality]], [[Semantic Composition]], [[Domain WSD]], [[Vector Space Models]], [[Semantics]], IIIT Hyderabad, York, Lexical Computing Ltd., [[Sketch Engine]], [[Resources]], [[POS Taggers]], [[Morphological Analyzers]]<br />
<br />
Please find some of the resources developed by me.<br />
<br />
== Compound Noun Compositionality Dataset ==<br />
<br />
[http://sivareddy.in/papers/files/ijcnlp_compositionality_data.tgz '''Compositionality Dataset'''] described in [http://sivareddy.in/papers/ijcnlp2011empirical.pdf Reddy, McCarthy and Manandhar (2011, IJCNLP)]. [http://dianamccarthy.co.uk/downloads.html Alternate download link] from [http://dianamccarthy.co.uk/ Diana McCarthy]<br />
<br />
== POS Taggers, Corpora, Lemmatizers, Morph Analyzers for Indian Languages ==<br />
<br />
Most of these tools are developed by the methods described in [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Reddy and Sharoff (2011, CLIA @ IJCNLP)]. Some of the taggers are built using cross-lingual resources and some using mono-lingual resources. Please read corresponding README's of each tool for additional information. This work is supported by [http://sketchengine.co.uk Sketch Engine] and [http://corpus.leeds.ac.uk/it/ Intellitext project]. If you need resources for any other Indian languages, please contact me.<br />
<br />
=== Kannada Tools ===<br />
<br />
[http://sivareddy.in/papers/files/kannada-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/kannada.sample.out.txt Sample Output of the tagger] For the complete corpus described in the paper, please contact me. [http://corpus.leeds.ac.uk/tools/ Alternate download link] from [http://www.comp.leeds.ac.uk/ssharoff/ Serge Sharoff]<br />
<br />
=== Telugu Tools ===<br />
<br />
[http://sivareddy.in/papers/files/telugu-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/telugu.sample.out.txt Sample Output of the tagger]<br />
<br />
=== Hindi Tools ===<br />
<br />
[http://sivareddy.in/papers/files/hindi-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/hindi.sample.out.txt Sample Output of the tagger] <br />
<br />
== Indonesian and Malay morphological analyzer, part-of-speech (POS) tagger, Machine Translation System ==<br />
<br />
With support from [http://sketchengine.co.uk Sketch Engine], I have made few contributions to the [http://wiki.apertium.org/wiki/Main_Page Apertium] Indonesian-Malay language pair. All the tools can be downloaded from svn repository https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms/ To download use the command "svn co https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms/" <br /></div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Sketch_Engine&diff=9334Sketch Engine2012-05-11T18:06:26Z<p>Sivareddy: Sketch Engine Tutorial</p>
<hr />
<div>= Sketch Engine =<br />
<br />
== 1. Background ==<br />
The Sketch Engine is a web-based program which takes as its input a corpus of any language with an appropriate level of linguistic mark-up. The Sketch Engine has a number of language-analysis functions, the core ones being:<br />
* '''the Concordancer''' A program which displays all occurrences from the corpus for a given query. The program is very powerful with a wide variety of query types and many different ways of displaying and organising the results.<br />
* '''the Word Sketch program''' This program provides a corpus-based summary of a word's grammatical and collocational behaviour. It will be described below in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted/#wordsketchid section 5].<br />
<br />
For the purposes of this guide, we use examples based on the Sketch Engine loaded with a sample corpus of English, the British National Corpus (BNC). For more information about the Sketch Engine, see [https://trac.sketchengine.co.uk/wiki/SkE/DocsIndex:sketch-engine-elx04.pdf Kilgarriff et al 2004 in Proc EURALEX]. For more information about the BNC, see [http://www.natcorp.ox.ac.uk/ http://www.natcorp.ox.ac.uk/]. <br />
<br />
<br />
Most terminology is defined as it is encountered below, however for a full glossary please see our [https://trac.sketchengine.co.uk/wiki/SkE/Help/JargonBuster Jargon Buster]<br />
<br />
<br />
== 2. Home page ==<br />
The software is on the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. In what follows, we have added links to this website. To view these links you will need to login to the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. After following a link in this tutorial, you can click the back icon in your browser to get back to this tutorial (alternatively, if you '''right click''' you can open the link in a different window or tab). You can follow the instructions below in a separate window so that you can compare what you see in your working screen with the links and descriptions given in this tutorial.<br />
<br />
Also, please note that if you are using a customer specific installation of Sketch Engine, rather than the http://www.sketchengine.co.uk/ website, the appearance of your screen may be slightly different, for example with regard to the colour, logos or text formatting. <br />
<br />
If you are not a registered user yet, we recommend that you set up a free Sketch Engine trial account before reading on, so that you can look at the examples on the [https://trac.sketchengine.co.uk/wiki/Corpora/BNC BNC] referenced below. Where possible we also provide alternative links to the same examples on the open [http://acl-arc.comp.nus.edu.sg/ ACL Anthology Reference Corpus], which you can open without logging in. Note though that some of the text below relates specifically to the results on BNC and you will see different data and different numbers on ACL ARC.<br />
<br />
Follow the links from [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/] page to either set up an account, or log in. The "home" screen looks like this: [http://the.sketchengine.co.uk/auth/corpora/ click here].<br />
<br />
Wherever you are in Sketch Engine, the link back to this home page is always displayed at the top right hand corner. Likewise you can always see "Settings", which allows you to update personal information and your password, and the "Log out" link.<br />
<br />
On the left hand side, you see options for creating corpora and a few other tools.<br />
<br />
In the main panel you can select your corpus . Here we want to explore the British National Corpus, so we click on that.<br />
<br />
If you prefer to work with an open corpus, you can go to the [http://the.sketchengine.co.uk/open/ list of open corpora] and click on the ACL Anthology Reference Corpus.<br />
<br />
== 3. Generating a concordance ==<br />
Your screen should then look like the link below:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/bnc2; click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/aclarc; click here (ACL ARC; no login required)]<br />
<br />
In the left hand side panel the option:<br />
* '''Concordance''' will always bring you back to this screen<br />
<br />
while:<br />
* '''Word List'''<br />
* '''Word Sketch'''<br />
* '''Thesaurus'''<br />
* '''Find X'''<br />
* '''Sketch-Diff'''<br />
<br />
take you to other tools which will be described in the sections below. <br />
<br />
To generate a concordance, you enter the main search term in the ([https://trac.sketchengine.co.uk/wiki/SkE/Help/SimpleQuery simple]) query box in the main panel of the screen.<br />
<br />
If, like the BNC, the corpus is lemmatized, the terms will match the lemma (the stemmed form) as well as the word. If you enter ''save'', the Sketch Engine will generate a concordance of all of the following:<br />
i) ''save-saved-saves-saving'' (verb)[[BR]]<br />
ii) ''save-save''s (noun - what goalkeepers make)[[BR]]<br />
iii) ''save'' (preposition: ''everyone was killed save Franco himself'')<br />
<br />
You can also enter phrases in the query box.<br />
<br />
To make more specific searches, you can select from the dropdown "Query Type" menu. This allows you to make specific types of queries:<br />
<br />
<br />
* simple: is the standard query which will match the lemma as well as the word as described above<br />
* lemma: will again match any lemma but here you can specify the part of speech (PoS i.e. the grammatical class e.g. noun, verb, adjective etc...). This option will not work for phrases. (Here and below we assume the corpus is, like the BNC, lemmatized and part-of-speech tagged. If it is not, not all of these query type options are available.)<br />
* phrase: will match a phrase e.g. ''runs away'', and any capitalised variant e.g. ''Runs away'', but will not match the lemma, so in this example ''run away'' will not be found.<br />
* Word form will match any word form exactly, you can select the PoS (e.g. noun or verb). You can also select whether you wish the system to match the exact capitisation you entered using "match case". For example, this will enable you to search for ''Bush'' rather than ''bush ''.<br />
* character matches a character string. For example, ''ate'' will match words containing this character sequence. This might be particularly useful in languages where tokenisation is difficult.<br />
* CQL: is for inputting complex queries using Corpus Query Language, described in [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying Corpus Querying and Grammar Writing]. "Default attribute" controls how CQL queries will be understood. The "tagset summary" box gives details of the part-of-speech tags used in the tagging. <br />
<br />
<br />
If you do not want to specify context any more precisely, you are now ready to hit the "Make Concordance" button and see the concordance. You will find more information about manipulating the output in [https://trac.sketchengine.co.uk/wiki/SkE/GettingStarted#concres Section 4] below. Note that when you have obtained the concordance you can always get back to the query entry form described here by clicking on "Concordance" at the top of the left hand side panel. The next sections explain how to limit your search to a specific context or text type.<br />
<br />
For the purposes of reading the following context and text type sections, make sure you are at the concordance entry form (by clicking concordance at the top of the left hand side menu) select "lemma" as the query type in the concordance entry form. For future reference note that all the options from this section are available with all the options described in the following sections on context and text type.<br />
<br />
=== The Context section ===<br />
<br />
Now open the Context section by clicking on the "Context" expert option in the left hand side panel.<br />
<br />
With the Context option you can make various specifications on the lemmas and/or PoS in the words surrounding your query. For both the lemma and PoS constraints you can indicate whether the system should look for the lemmas (or PoS) to the left or right or at either side (both) of your query term. You also get a chance to specify how many tokens (words or punctuation), up to 15, of context to search for these constraints. You enter any number of lemmas or PoS and can specify if they should "all" apply, or whether "any" or "none" should be matched.<br />
<br />
Here are some examples:<br />
<br />
1. you want to search for the lemma ''shake'' (verb) followed by ''head'' (noun), to find instances such as ''she shook her head'', ''if you agree shake your head'', and ''shaking their heads in disbelief...'' You can do the following:<br />
* either type ''shake'' in the query box with PoS verb. Then type ''head'' in the Context lemma box PoS noun and specify Right and a window size (say 3 tokens)<br />
* or type ''head'' in the query box with PoS noun. Then type ''shake'' in the Context lemma box with PoS verb and specify Left and a window size (say 3 tokens)<br />
The results will be the same whichever route you take.<br />
<br />
2. you want to search for the verb ''taste'' followed by ''any'' adjective; since a following adjective may appear either in position 1 (''it tastes horrible''), position 2 (''it tastes really delicious''), or even position 3 (''it didn't taste quite so good''). Type ''taste'' in the query box, with query type lemma and PoS "verb". Then - in the Context area - select "adjective" from the PoS list and specify Right and a window size of 3 tokens. This generates a concordance of 480 lines in the BNC. You can further refine your search by specifying two PoS in the Context section. In this case, if you select both "adjective" and "adverb" by holding the CTRL key to select more than one PoS you will get a smaller concordance of 125 lines, with examples such as ''it tastes bloody awful'' and ''it tastes surprisingly good''. <br />
<br />
You can clear any boxes with the "clear all" option at the bottom of the screen.<br />
<br />
There are many more complex searches you can carry out using this feature - it is worth trying things out to see what is possible. For example, you could further refine the first search here (with ''head''=Lemma and ''shake''=Left Context ) by also specifying a PoS in the Right Context. Thus specifying "adverb" in the Right Context will generate lines such as ''shook his head '''disapprovingly''''', whereas specifying "noun" will generate ''shook their heads in '''agreement'''''. There are very many searches one might try, though in practice most searches are relatively simple.<br />
<br />
Context searches can also be used to exclude unwanted items: thus you could input a query of ''weapons of'' using the phrase option for the Query type (described in the section above), then exclude "destruction" by typing it into the Context Lemma box, specifying Right and then selecting "None" from the drop-down list. This returns a concordance for any lines containing the string ''weapons of'' ''without'' the word ''destruction''.<br />
<br />
<br />
=== The Text Type section ===<br />
Return to the concordance query form, if you are not already there, by clicking on "Concordance" at the top of the left hand side menu. Close the Context section by clicking on the expert option "Context" and select the option "Text Type", again, in the left hand side panel. <br />
<br />
With the '''Text Types''' option you can limit your search to a part of the corpus. If you want to see how a word behaves in the spoken part of the corpus, enter the word in the search box (or combine with other search specifications as described above) and tick the boxes for "Spoken context governed" and "Spoken demographic". Your concordance will contain only spoken-language examples. The partitions available depend on the text types (also referred to as header information or metadata) provided in the corpus data.<br />
<br />
== 4. Manipulating your concordance output == #concres<br />
Once you have generated a concordance, there are several options for increasing its usefulness. Click on "Concordance", chose a query type simple search and enter the word ''haunt'' and click "Make Concordance".<br />
<br />
<br />
The concordance screen looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Fbnc2&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Faclarc&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (ACL ARC; no login required)]<br />
<br />
As before, the options above the bar in the left hand side will take you to other parts of the program and are described below. The options below the horizontal bar in the left hand side menu allow you to work on this concordance. <br />
<br />
The panel directly above the concordance tells you which corpus you are using, and how many hits match your search item. For ''haunt'', there are 1098 concordance lines.<br />
<br />
=== Moving around the concordance ===<br />
You can move from one part of the concordance to another either by specifying a number in the '''Page''' box and selecting '''Go''', or by clicking on '''Next''', '''Last''', '''First''' or '''Previous'''.<br />
<br />
=== Finding out about a particular concordance line ===<br />
If you click on one of the highlighted node words, more of its context appears in the panel at the bottom of the screen and you can further expand the context by clicking on '''expand left''' and/or '''expand right'''. To hide this extra context click on the "-" in the top left hand of the context window.<br />
<br />
To get information about the source-text a particular concordance line comes from, click the document-id code at the left-hand end of the relevant line (assuming you have not changed the "View option" relating to "references", see below). This brings up "header" information in the bottom pane.<br />
<br />
=== The concordance menu ===#concmenu<br />
<br />
In the lower section of the left hand side panel there are various options for refining your concordance. <br />
<br />
* '''View Options''': takes you to a new screen in the main panel that allows you to change the concordance view in various ways. To summarise the functions available when you select View Options (NB if you do click '''view options''' then you can select '''view concordance''' to get back) :<br />
* the '''Attributes''' column allows you to change from the default display (in which only the text is visible in the concordance line) to a number of alternative views in which you can see PoS-tags, lemmatized forms, and any other fields of information, either for the node word only ("KWIC tokens only") or for every word in the concordance line ("For each token"). The function can be useful for finding out why an unexpected corpus line has matched a query, as the cause is sometimes an incorrect PoS-tag or lemmatization <br />
* the '''Structures '''column allows you to change from the default display to show the beginning and end tags for structures such as sentences, paragraphs and documents. <br />
* the '''References''' column dictates the type of information regarding the source texts which appears (in blue) at the left-hand end of the concordance line. The default is an identifier for the document that the concordance line is taken from. Any other fields of information about corpus documents can be selected and the value that the concordance line has for that field will then be seen. For example, if the corpus encodes whether a document is imaginative writing or not, and the appropriate feature (e.g. in the BNC this is "Domain for written corpus texts") is selected in the References column and '''change view options''' is clicked, then the domain of the concordance lines will be displayed in the left hand column and we can see those that come from an "imaginative" text.<br />
* the '''Page Size''' box (bottom left) allows you to specify a longer page length for the display: the default is that each page of concordances contains 20 lines. (Increasing the Page Size will slow down initial retrieval of the concordance.) <br />
* '''KWIC Context size''' allows you to specify the size of the context window in number of characters<br />
* '''Sort good dictionary examples''' allows you to specify how many lines of 'good' examples that the system should automatically rank at the top of the concordance according to the GDEX program (see http://www.kilgarriff.co.uk/Publications/2008-KilgEtAl-euralex-gdex.doc)<br />
* '''Icon for one-click sentence copying''': You can add an icon for copying lines from the concordance <br />
* '''Allow multiple lines selection''' - Allow user to select and/or copy more than one line at once.<br />
* '''XML template for one-click copying''' (A feature used for specific projects only)<br />
<br />
* '''KWIC/Sentence''' lets you toggle between standard KWIC concordance view (which appears by default) and full sentence view.<br />
<br />
* '''Save''' gives you options for sorting the concordance. You can specify whether the output is text or xml, how many pages, whether a heading is included, whether the lines are numbered, whether the KWIC are aligned in the output and the maximum number of lines.<br />
<br />
* '''Sort''': Sorting is often a quick way of revealing patterns. If you select this option in the left hand side panel you obtain a screen in the main panel with various complex options for sorting (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sortconc the page specific help on Sort]) you can alternatively use the other options below '''sort''' to simply sort by:<br />
* '''Left:''' one token (word or punctuation) to the left<br />
* '''Right''': one token to the right<br />
* '''Node''': the KWIC (also referred to as the node word) <br />
* '''References''': sorting according to whichever references you display to the left of the concordance lines (as described in view options above).<br />
* '''Shuffle''': this shuffles the concordance so that the lines are arbitrarily ordered. Since the sample option described below always provides the same ordering for a give sized sample, this allows you to jumble the concordance so you can view only a portion of the concordance or your sample, without bias from the ordering.<br />
<br />
* '''Sample''': This allows you to create a random sample of the corpus lines. You can specify the size of the sample (i.e. the number of lines) or use the default of 250. For example, if you search for ''play'' (verb) and decide that you do not want to analyse 37,632 lines, use this option to reduce this to a manageable number. (see also [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/sampleconc specific help on the random sample page])<br />
<br />
* '''Filter''': This allows you to specify constraints on the context of your KWIC to retrieve a subset of your concordance. See [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/filterconc the filter page specific help]<br />
<br />
* '''Frequency''' allows you to produce two types of frequency information regarding your search term:<br />
1. '''Multilevel frequency distribution''' shows the frequency of each form of a given lemma. To see how this works, make a concordance for ''forge'' (verb): when the concordance displays, select '''Frequency''' and use the '''Multilevel frequency distribution''' section. The (default) "first level" shows you the frequencies of the forms ''forge'', ''forged'', ''forging'' and ''forges''. The second and third levels allow more complex searches of this type: for example if you check "second level" and select "1R" (=word one position to right of node word) you will see which words appear in this position and how frequent each of these words is. <br />
2. '''Text type frequency distribution''' shows how your search term is distributed through the texts in the corpus. You may find, for example, that a word like ''police'' appears significantly more often in newspaper texts than in other text types. This is a potentially useful tool which could show you - for example - that a particular medical term is not restricted to specialised medical discourse. As with the "references" column in the "View Options" screen, the actual values you can select depend on the corpus you are using, and how it has been set up in the Sketch Engine. <br />
* The frequency option is also described in [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/freqconc the page specific help on frequency]. You can alternatively use the simpler frequency options below '''Frequency''' to simply sort by:<br />
* '''Node tags''': the PoS tags for all the KWIC word forms (node word types)<br />
* '''Node forms''': the word forms for all the KWIC word forms<br />
* '''Doc IDs''': frequency distribution over the document ids<br />
* '''Text Types''': frequency distribution over all the text types specified for the corpus<br />
<br />
* '''Collocations''' allows you to generate lists of words that co-occur frequently with your node word (its "collocates"). Where word sketches (see the next section) are available, they give a more sophisticated account of collocates in most cases. (see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/collocconc collocations page specific help])<br />
<br />
* '''Original Concordance''': is visible if you have refined your concordance. If you select this you can get rid of the refinements and return to the original concordance.<br />
<br />
* '''!ConcDesc''': provides a technical description of your query. This is useful for programmers and technical people.<br />
<br />
== 5. The Word Sketch function == #wordsketchid<br />
<br />
A Word Sketch is a corpus-based summary of a word's grammatical and collocational behaviour. <br />
<br />
Click on '''Word Sketch''' in the left hand side main menu (top section of the left hand side menu), and this takes you to the Word Sketch entry form, which looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/bnc2;lemma=;lpos= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/aclarc;lemma=;lpos= click here (ACL ARC; no login required)]<br />
<br />
Choose a lemma and specify its part of speech using the drop-down list. Word Sketches are typically available for nouns, verbs, and adjectives and can be available for other word classes depending on the grammatical definitions supplied to the sketch engine (see [https://trac.sketchengine.co.uk/wiki/SkE/CorpusQuerying#wordsketchdefs the documentation on grammatical relation definitions] for more information). Word sketches also depend on the availability of substantial amounts of data, so if you try to create a Word Sketch for a fairly rare item you will see a message saying there is no Word Sketch available. (This is perfectly reasonable: the point of the Word Sketches is to provide helpful summaries when there is too much corpus data to scan efficiently using a concordance; but when there are only a few concordance lines it is easy enough to analyse them all manually.) In general, you need several hundred instances of a word to make a useful word sketch.<br />
<br />
This [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch?corpname=preloaded%2Fbnc2&lemma=challenge&lpos=-n&usesubcorp=&minfreq=auto&minscore=0.0&maxitems=25&sort_ws_columns=s&clustercolls=0&structured=0&structured=1&minsim=0.15&selgrlist=and%2For&selgrlist=object&selgrlist=object_of&selgrlist=subject&selgrlist=subject_of&selgrlist=adj_subject_of&selgrlist=adj_subject&selgrlist=predicate_of&selgrlist=predicate&selgrlist=modifier&selgrlist=modifies&selgrlist=modifier&selgrlist=possession&selgrlist=possessor&selgrlist=adj_comp&selgrlist=adj_comp_of&selgrlist=np_adj_comp&selgrlist=np_adj_comp_of&selgrlist=particle&selgrlist=part_intrans&selgrlist=part_trans&selgrlist=pp_%25s&selgrlist=pp_obj_%25s&selgrlist=part_%25s_obj&selgrlist=np_np&selgrlist=np_pp&selgrlist=np_adv&selgrlist=np_sfin&selgrlist=np_VPbare&selgrlist=np_VPing&selgrlist=np_VPto&selgrlist=part_pp&selgrlist=prep_ing&selgrlist=prep_Sing&selgrlist=prep_wh&selgrlist=quote&selgrlist=Sbare&selgrlist=Scond&selgrlist=Sfin&selgrlist=Sforto&selgrlist=Sing&selgrlist=Swh&selgrlist=Swhether&selgrlist=VPto&selgrlist=VPing&selgrlist=there%2B&selgrlist=it%2B&selgrlist=poss&selgrlist=reflexive&selgrlist=passive link] shows a Word Sketch for the noun ''challenge''. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsketch?corpname=preloaded%2Faclarc&lemma=challenge&lpos=-n&minfreq=auto&minscore=0.0&maxitems=25&sort_ws_columns=s&tbl_template=none&tbl_no_examples=6&clustercolls=0&structured=0&structured=1&minsim=0.15&selgrlist=and%2For&selgrlist=object&selgrlist=object_of&selgrlist=subject&selgrlist=subject_of&selgrlist=adj_subject_of&selgrlist=adj_subject&selgrlist=predicate_of&selgrlist=predicate&selgrlist=pro_object&selgrlist=pro_subject&selgrlist=modifier&selgrlist=modifies&selgrlist=possessed&selgrlist=possessor&selgrlist=pro_possessor&selgrlist=wh_comp&selgrlist=infin_comp&selgrlist=ing_comp&selgrlist=passive&selgrlist=reflexive&selgrlist=it%2B&selgrlist=pp_%25s&selgrlist=np_adj_comp&selgrlist=np_adj_comp_of&selgrlist=adj_comp&selgrlist=adj_comp_of&selgrlist=part_intrans&selgrlist=part_trans&selgrlist=part_%25s_obj Alternative link] for ACL ARC.)<br />
<br />
Each column show the words that typically combine with ''challenge'' in a particular grammatical relations (or "gramrels"). Most of these gramrels are self-explanatory. For example, "object_of" lists - in order of statistical significance rather than raw frequency - the verbs that most typically occupy the verb slot in cases where ''challenge'' is the object of a verb. Most of the data is lexicographically relevant, though one might query the adjectival modifier ''larval'': it turns out that ''larval challenge'' is a technical term used in parasitology, discussed in a BNC document.<br />
<br />
You can at any time switch between Concordance mode and Word Sketch mode, and this is a useful way of getting more information about a particular word combination. Thus, if you want to look at examples of "''pose'' + ''challenge''" (where ''challenge'' is the direct object of ''pose''), simply click on the number next to ''pose'' in the "object_of" list ('''92''') and you will be taken directly to a concordance showing all instances of this combination.<br />
<br />
== 6. The Thesaurus function == #distributionalthesaurusid<br />
The software checks to see which words occur with the same collocates as other words, and on the basis of this data it generates a "distributional thesaurus". A distributional thesaurus is an automatically produced "thesaurus" which finds words that tend to occur in similar contexts as the target word. It is '''not''' a man made thesaurus of synonyms. The thesaurus function lists, for any given adjective, noun or verb, the other words ''most similar'' to it in in terms of grammatical and collocational behaviour.<br />
<br />
Click on the '''Thesaurus''' link on the left hand side main (top) menu and then input the word with PoS that you are interested in. <br />
<br />
For help on the advanced options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/Thesaurus the thesaurus help page].<br />
<br />
== 7. The Sketch Difference function == #sketchdiffid<br />
Sketch Difference is a neat way of comparing two very similar words: it shows those patterns and combinations that the two items have in common, and also those patterns and combinations that are more typical of, or unique to, one word rather than the other. You can also use the function to compare the same lemma in two different parts of the corpus, or to compare two different word forms e.g. ''men'' and ''man''. Click on any word in a Thesaurus entry for a word, and you will be taken straight to a screen showing the Sketch Difference between the two words. Alternatively, you can click on '''Sketch-Diff''' on the left hand side panel and this will take you to the word sketch difference entry form which gives you more options.<br />
<br />
Suppose you want to compare ''clever '' and ''intelligent''. In the thesaurus entry for ''clever'', ''intelligent '' comes top of the list: it is statistically the most similar word in terms of shared contexts of occurrence. Click on ''intelligent'' and you are taken to a new screen which is in three main parts: the first part shows "Common Patterns" (those combinations where ''clever'' and ''intelligent'' behave quite similarly), the second and third parts show "clever only patterns" and "intelligent only patterns". The screen looks like this [http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Fbnc2&lemma=clever&lpos=-j&usesubcorp=;lemma2=intelligent click here]. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Faclarc&lemma=clever&lpos=-j&diff_by=lemma&lemma2=intelligent Alternative link] for ACL ARC.) <br />
<br />
In the "Common Patterns" part, there are four numbers next to each collocate. The first two indicate the frequency of co-occurrence with the first and second lemma, the last two show the salience scores for the collocate with both lemmas. All collocates are sorted according to maximum of the two salience scores and coloured according to difference between the scores.<br />
<br />
Try this out, and look at the difference in the "and/or" lists: people can be "intelligent and articulate/thoughtful/sensitive" etc, but they are often "clever and devious/cunning/brave". <br />
<br />
For more information on the other options see [https://trac.sketchengine.co.uk/wiki/SkE/Help/PageSpecificHelp/SketchDiff the Word Sketch Difference help]<br />
<br />
== 8. The Search function ==<br />
<br />
From any screen you can do a "simple" '''Search''' in any corpus by using the field and drop down list in the horizontal panel which appears just beneath the very top bar in which you can search the Help documentation. This search function provides a short cut to a simple concordance<br />
<br />
== 9. Other functions ==<br />
<br />
For an explanation of other functions in the left hand side margin you can click the help links marked with a '''?'''<br />
<br />
----<br />
Click [https://trac.sketchengine.co.uk/wiki/WikiStart here] for the Start Page for Sketch Engine Documentation.</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Sketch_Engine&diff=9333Sketch Engine2012-05-11T17:53:10Z<p>Sivareddy: Getting started with Sketch Engine - A Corpus Concordancer</p>
<hr />
<div>= Sketch Engine =<br />
<br />
== 1. Background ==<br />
The Sketch Engine is a web-based program which takes as its input a corpus of any language with an appropriate level of linguistic mark-up. The Sketch Engine has a number of language-analysis functions, the core ones being:<br />
* __the Concordancer__ A program which displays all occurrences from the corpus for a given query. The program is very powerful with a wide variety of query types and many different ways of displaying and organising the results.<br />
* __the Word Sketch program__ This program provides a corpus-based summary of a word's grammatical and collocational behaviour. It will be described below in [wiki:SkE/GettingStarted/#wordsketchid section 5].<br />
<br />
For the purposes of this guide, we use examples based on the Sketch Engine loaded with a sample corpus of English, the British National Corpus (BNC). For more information about the Sketch Engine, see [attachment:wiki:SkE/DocsIndex:sketch-engine-elx04.pdf Kilgarriff et al 2004 in Proc EURALEX]. For more information about the BNC, see [http://www.natcorp.ox.ac.uk/ http://www.natcorp.ox.ac.uk/]. <br />
<br />
<br />
Most terminology is defined as it is encountered below, however for a full glossary please see our [wiki:SkE/Help/JargonBuster Jargon Buster]<br />
<br />
<br />
== 2. Home page ==<br />
The software is on the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. In what follows, we have added links to this website. To view these links you will need to login to the Sketch Engine website: [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/]. After following a link in this tutorial, you can click the back icon in your browser to get back to this tutorial (alternatively, if you '''right click''' you can open the link in a different window or tab). You can follow the instructions below in a separate window so that you can compare what you see in your working screen with the links and descriptions given in this tutorial.<br />
<br />
Also, please note that if you are using a customer specific installation of Sketch Engine, rather than the http://www.sketchengine.co.uk/ website, the appearance of your screen may be slightly different, for example with regard to the colour, logos or text formatting. <br />
<br />
If you are not a registered user yet, we recommend that you set up a free Sketch Engine trial account before reading on, so that you can look at the examples on the [wiki:Corpora/BNC BNC] referenced below. Where possible we also provide alternative links to the same examples on the open [http://acl-arc.comp.nus.edu.sg/ ACL Anthology Reference Corpus], which you can open without logging in. Note though that some of the text below relates specifically to the results on BNC and you will see different data and different numbers on ACL ARC.<br />
<br />
Follow the links from [http://www.sketchengine.co.uk/ http://www.sketchengine.co.uk/] page to either set up an account, or log in. The "home" screen looks like this: [http://the.sketchengine.co.uk/auth/corpora/ click here].<br />
<br />
Wherever you are in Sketch Engine, the link back to this home page is always displayed at the top right hand corner. Likewise you can always see "Settings", which allows you to update personal information and your password, and the "Log out" link.<br />
<br />
On the left hand side, you see options for creating corpora and a few other tools.<br />
<br />
In the main panel you can select your corpus . Here we want to explore the British National Corpus, so we click on that.<br />
<br />
If you prefer to work with an open corpus, you can go to the [http://the.sketchengine.co.uk/open/ list of open corpora] and click on the ACL Anthology Reference Corpus.<br />
<br />
== 3. Generating a concordance ==<br />
Your screen should then look like the link below:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/bnc2; click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first_form?corpname=preloaded/aclarc; click here (ACL ARC; no login required)]<br />
<br />
In the left hand side panel the option:<br />
* '''Concordance''' will always bring you back to this screen<br />
<br />
while:<br />
* '''Word List'''<br />
* '''Word Sketch'''<br />
* '''Thesaurus'''<br />
* '''Find X'''<br />
* '''Sketch-Diff'''<br />
<br />
take you to other tools which will be described in the sections below. <br />
<br />
To generate a concordance, you enter the main search term in the ([wiki:SkE/Help/SimpleQuery simple]) query box in the main panel of the screen.<br />
<br />
If, like the BNC, the corpus is lemmatized, the terms will match the lemma (the stemmed form) as well as the word. If you enter ''save'', the Sketch Engine will generate a concordance of all of the following:<br />
i) ''save-saved-saves-saving'' (verb)[[BR]]<br />
ii) ''save-save''s (noun - what goalkeepers make)[[BR]]<br />
iii) ''save'' (preposition: ''everyone was killed save Franco himself'')<br />
<br />
You can also enter phrases in the query box.<br />
<br />
To make more specific searches, you can select from the dropdown "Query Type" menu. This allows you to make specific types of queries:<br />
<br />
<br />
* simple: is the standard query which will match the lemma as well as the word as described above<br />
* lemma: will again match any lemma but here you can specify the part of speech (PoS i.e. the grammatical class e.g. noun, verb, adjective etc...). This option will not work for phrases. (Here and below we assume the corpus is, like the BNC, lemmatized and part-of-speech tagged. If it is not, not all of these query type options are available.)<br />
* phrase: will match a phrase e.g. ''runs away'', and any capitalised variant e.g. ''Runs away'', but will not match the lemma, so in this example ''run away'' will not be found.<br />
* Word form will match any word form exactly, you can select the PoS (e.g. noun or verb). You can also select whether you wish the system to match the exact capitisation you entered using "match case". For example, this will enable you to search for ''Bush'' rather than ''bush ''.<br />
* character matches a character string. For example, ''ate'' will match words containing this character sequence. This might be particularly useful in languages where tokenisation is difficult.<br />
* CQL: is for inputting complex queries using Corpus Query Language, described in [wiki:SkE/CorpusQuerying Corpus Querying and Grammar Writing]. "Default attribute" controls how CQL queries will be understood. The "tagset summary" box gives details of the part-of-speech tags used in the tagging. <br />
<br />
<br />
If you do not want to specify context any more precisely, you are now ready to hit the "Make Concordance" button and see the concordance. You will find more information about manipulating the output in [wiki:SkE/GettingStarted#concres Section 4] below. Note that when you have obtained the concordance you can always get back to the query entry form described here by clicking on "Concordance" at the top of the left hand side panel. The next sections explain how to limit your search to a specific context or text type.<br />
<br />
For the purposes of reading the following context and text type sections, make sure you are at the concordance entry form (by clicking concordance at the top of the left hand side menu) select "lemma" as the query type in the concordance entry form. For future reference note that all the options from this section are available with all the options described in the following sections on context and text type.<br />
<br />
=== The Context section ===<br />
<br />
Now open the Context section by clicking on the "Context" expert option in the left hand side panel.<br />
<br />
With the Context option you can make various specifications on the lemmas and/or PoS in the words surrounding your query. For both the lemma and PoS constraints you can indicate whether the system should look for the lemmas (or PoS) to the left or right or at either side (both) of your query term. You also get a chance to specify how many tokens (words or punctuation), up to 15, of context to search for these constraints. You enter any number of lemmas or PoS and can specify if they should "all" apply, or whether "any" or "none" should be matched.<br />
<br />
Here are some examples:<br />
<br />
1. you want to search for the lemma ''shake'' (verb) followed by ''head'' (noun), to find instances such as ''she shook her head'', ''if you agree shake your head'', and ''shaking their heads in disbelief...'' You can do the following:<br />
* either type ''shake'' in the query box with PoS verb. Then type ''head'' in the Context lemma box PoS noun and specify Right and a window size (say 3 tokens)<br />
* or type ''head'' in the query box with PoS noun. Then type ''shake'' in the Context lemma box with PoS verb and specify Left and a window size (say 3 tokens)<br />
The results will be the same whichever route you take.<br />
<br />
2. you want to search for the verb ''taste'' followed by ''any'' adjective; since a following adjective may appear either in position 1 (''it tastes horrible''), position 2 (''it tastes really delicious''), or even position 3 (''it didn't taste quite so good''). Type ''taste'' in the query box, with query type lemma and PoS "verb". Then - in the Context area - select "adjective" from the PoS list and specify Right and a window size of 3 tokens. This generates a concordance of 480 lines in the BNC. You can further refine your search by specifying two PoS in the Context section. In this case, if you select both "adjective" and "adverb" by holding the CTRL key to select more than one PoS you will get a smaller concordance of 125 lines, with examples such as ''it tastes bloody awful'' and ''it tastes surprisingly good''. <br />
<br />
You can clear any boxes with the "clear all" option at the bottom of the screen.<br />
<br />
There are many more complex searches you can carry out using this feature - it is worth trying things out to see what is possible. For example, you could further refine the first search here (with ''head''=Lemma and ''shake''=Left Context ) by also specifying a PoS in the Right Context. Thus specifying "adverb" in the Right Context will generate lines such as ''shook his head __disapprovingly__'', whereas specifying "noun" will generate ''shook their heads in __agreement__''. There are very many searches one might try, though in practice most searches are relatively simple.<br />
<br />
Context searches can also be used to exclude unwanted items: thus you could input a query of ''weapons of'' using the phrase option for the Query type (described in the section above), then exclude "destruction" by typing it into the Context Lemma box, specifying Right and then selecting "None" from the drop-down list. This returns a concordance for any lines containing the string ''weapons of'' ''without'' the word ''destruction''.<br />
<br />
<br />
=== The Text Type section ===<br />
Return to the concordance query form, if you are not already there, by clicking on "Concordance" at the top of the left hand side menu. Close the Context section by clicking on the expert option "Context" and select the option "Text Type", again, in the left hand side panel. <br />
<br />
With the '''Text Types''' option you can limit your search to a part of the corpus. If you want to see how a word behaves in the spoken part of the corpus, enter the word in the search box (or combine with other search specifications as described above) and tick the boxes for "Spoken context governed" and "Spoken demographic". Your concordance will contain only spoken-language examples. The partitions available depend on the text types (also referred to as header information or metadata) provided in the corpus data.<br />
<br />
== 4. Manipulating your concordance output == #concres<br />
Once you have generated a concordance, there are several options for increasing its usefulness. Click on "Concordance", chose a query type simple search and enter the word ''haunt'' and click "Make Concordance".<br />
<br />
<br />
The concordance screen looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Fbnc2&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/first?corpname=preloaded%2Faclarc&queryselector=iqueryrow&iquery=haunt&lemma=&lpos=&phrase=&word=&wpos=&char=&cql=&default_attr=lc&fc_lemword_window_type=both&fc_lemword_wsize=5&fc_lemword=&fc_lemword_type=all&fc_pos_window_type=both&fc_pos_wsize=5&fc_pos_type=all&usesubcorp=&sca_bncdoc.genre=&sca_u.who= click here (ACL ARC; no login required)]<br />
<br />
As before, the options above the bar in the left hand side will take you to other parts of the program and are described below. The options below the horizontal bar in the left hand side menu allow you to work on this concordance. <br />
<br />
The panel directly above the concordance tells you which corpus you are using, and how many hits match your search item. For ''haunt'', there are 1098 concordance lines.<br />
<br />
=== Moving around the concordance ===<br />
You can move from one part of the concordance to another either by specifying a number in the '''Page''' box and selecting '''Go''', or by clicking on __Next__, __Last__, __First__ or __Previous__.<br />
<br />
=== Finding out about a particular concordance line ===<br />
If you click on one of the highlighted node words, more of its context appears in the panel at the bottom of the screen and you can further expand the context by clicking on __expand left__ and/or __expand right__. To hide this extra context click on the "-" in the top left hand of the context window.<br />
<br />
To get information about the source-text a particular concordance line comes from, click the document-id code at the left-hand end of the relevant line (assuming you have not changed the "View option" relating to "references", see below). This brings up "header" information in the bottom pane.<br />
<br />
=== The concordance menu ===#concmenu<br />
<br />
In the lower section of the left hand side panel there are various options for refining your concordance. <br />
<br />
* '''View Options''': takes you to a new screen in the main panel that allows you to change the concordance view in various ways. To summarise the functions available when you select View Options (NB if you do click '''view options''' then you can select '''view concordance''' to get back) :<br />
* the '''Attributes''' column allows you to change from the default display (in which only the text is visible in the concordance line) to a number of alternative views in which you can see PoS-tags, lemmatized forms, and any other fields of information, either for the node word only ("KWIC tokens only") or for every word in the concordance line ("For each token"). The function can be useful for finding out why an unexpected corpus line has matched a query, as the cause is sometimes an incorrect PoS-tag or lemmatization <br />
* the '''Structures '''column allows you to change from the default display to show the beginning and end tags for structures such as sentences, paragraphs and documents. <br />
* the '''References''' column dictates the type of information regarding the source texts which appears (in blue) at the left-hand end of the concordance line. The default is an identifier for the document that the concordance line is taken from. Any other fields of information about corpus documents can be selected and the value that the concordance line has for that field will then be seen. For example, if the corpus encodes whether a document is imaginative writing or not, and the appropriate feature (e.g. in the BNC this is "Domain for written corpus texts") is selected in the References column and '''change view options''' is clicked, then the domain of the concordance lines will be displayed in the left hand column and we can see those that come from an "imaginative" text.<br />
* the '''Page Size''' box (bottom left) allows you to specify a longer page length for the display: the default is that each page of concordances contains 20 lines. (Increasing the Page Size will slow down initial retrieval of the concordance.) <br />
* '''KWIC Context size''' allows you to specify the size of the context window in number of characters<br />
* '''Sort good dictionary examples''' allows you to specify how many lines of 'good' examples that the system should automatically rank at the top of the concordance according to the GDEX program (see http://www.kilgarriff.co.uk/Publications/2008-KilgEtAl-euralex-gdex.doc)<br />
* '''Icon for one-click sentence copying''': You can add an icon for copying lines from the concordance <br />
* '''Allow multiple lines selection''' - Allow user to select and/or copy more than one line at once.<br />
* '''XML template for one-click copying''' (A feature used for specific projects only)<br />
<br />
* '''KWIC/Sentence''' lets you toggle between standard KWIC concordance view (which appears by default) and full sentence view.<br />
<br />
* '''Save''' gives you options for sorting the concordance. You can specify whether the output is text or xml, how many pages, whether a heading is included, whether the lines are numbered, whether the KWIC are aligned in the output and the maximum number of lines.<br />
<br />
* '''Sort''': Sorting is often a quick way of revealing patterns. If you select this option in the left hand side panel you obtain a screen in the main panel with various complex options for sorting (see [wiki:SkE/Help/PageSpecificHelp/sortconc the page specific help on Sort]) you can alternatively use the other options below '''sort''' to simply sort by:<br />
* '''Left:''' one token (word or punctuation) to the left<br />
* '''Right''': one token to the right<br />
* '''Node''': the KWIC (also referred to as the node word) <br />
* '''References''': sorting according to whichever references you display to the left of the concordance lines (as described in view options above).<br />
* '''Shuffle''': this shuffles the concordance so that the lines are arbitrarily ordered. Since the sample option described below always provides the same ordering for a give sized sample, this allows you to jumble the concordance so you can view only a portion of the concordance or your sample, without bias from the ordering.<br />
<br />
* '''Sample''': This allows you to create a random sample of the corpus lines. You can specify the size of the sample (i.e. the number of lines) or use the default of 250. For example, if you search for ''play'' (verb) and decide that you do not want to analyse 37,632 lines, use this option to reduce this to a manageable number. (see also [wiki:SkE/Help/PageSpecificHelp/sampleconc specific help on the random sample page])<br />
<br />
* '''Filter''': This allows you to specify constraints on the context of your KWIC to retrieve a subset of your concordance. See [wiki:SkE/Help/PageSpecificHelp/filterconc the filter page specific help]<br />
<br />
* '''Frequency''' allows you to produce two types of frequency information regarding your search term:<br />
1. '''Multilevel frequency distribution''' shows the frequency of each form of a given lemma. To see how this works, make a concordance for ''forge'' (verb): when the concordance displays, select '''Frequency''' and use the '''Multilevel frequency distribution''' section. The (default) "first level" shows you the frequencies of the forms ''forge'', ''forged'', ''forging'' and ''forges''. The second and third levels allow more complex searches of this type: for example if you check "second level" and select "1R" (=word one position to right of node word) you will see which words appear in this position and how frequent each of these words is. <br />
2. '''Text type frequency distribution''' shows how your search term is distributed through the texts in the corpus. You may find, for example, that a word like ''police'' appears significantly more often in newspaper texts than in other text types. This is a potentially useful tool which could show you - for example - that a particular medical term is not restricted to specialised medical discourse. As with the "references" column in the "View Options" screen, the actual values you can select depend on the corpus you are using, and how it has been set up in the Sketch Engine. <br />
* The frequency option is also described in [wiki:SkE/Help/PageSpecificHelp/freqconc the page specific help on frequency]. You can alternatively use the simpler frequency options below '''Frequency''' to simply sort by:<br />
* '''Node tags''': the PoS tags for all the KWIC word forms (node word types)<br />
* '''Node forms''': the word forms for all the KWIC word forms<br />
* '''Doc IDs''': frequency distribution over the document ids<br />
* '''Text Types''': frequency distribution over all the text types specified for the corpus<br />
<br />
* '''Collocations''' allows you to generate lists of words that co-occur frequently with your node word (its "collocates"). Where word sketches (see the next section) are available, they give a more sophisticated account of collocates in most cases. (see [wiki:SkE/Help/PageSpecificHelp/collocconc collocations page specific help])<br />
<br />
* '''Original Concordance''': is visible if you have refined your concordance. If you select this you can get rid of the refinements and return to the original concordance.<br />
<br />
* '''!ConcDesc''': provides a technical description of your query. This is useful for programmers and technical people.<br />
<br />
== 5. The Word Sketch function == #wordsketchid<br />
<br />
A Word Sketch is a corpus-based summary of a word's grammatical and collocational behaviour. <br />
<br />
Click on '''Word Sketch''' in the left hand side main menu (top section of the left hand side menu), and this takes you to the Word Sketch entry form, which looks like this:<br />
<br />
[http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/bnc2;lemma=;lpos= click here (BNC)] or [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch_form?corpname=preloaded/aclarc;lemma=;lpos= click here (ACL ARC; no login required)]<br />
<br />
Choose a lemma and specify its part of speech using the drop-down list. Word Sketches are typically available for nouns, verbs, and adjectives and can be available for other word classes depending on the grammatical definitions supplied to the sketch engine (see [wiki:SkE/CorpusQuerying#wordsketchdefs the documentation on grammatical relation definitions] for more information). Word sketches also depend on the availability of substantial amounts of data, so if you try to create a Word Sketch for a fairly rare item you will see a message saying there is no Word Sketch available. (This is perfectly reasonable: the point of the Word Sketches is to provide helpful summaries when there is too much corpus data to scan efficiently using a concordance; but when there are only a few concordance lines it is easy enough to analyse them all manually.) In general, you need several hundred instances of a word to make a useful word sketch.<br />
<br />
This [http://the.sketchengine.co.uk/bonito/run.cgi/wsketch?corpname=preloaded%2Fbnc2&lemma=challenge&lpos=-n&usesubcorp=&minfreq=auto&minscore=0.0&maxitems=25&sort_ws_columns=s&clustercolls=0&structured=0&structured=1&minsim=0.15&selgrlist=and%2For&selgrlist=object&selgrlist=object_of&selgrlist=subject&selgrlist=subject_of&selgrlist=adj_subject_of&selgrlist=adj_subject&selgrlist=predicate_of&selgrlist=predicate&selgrlist=modifier&selgrlist=modifies&selgrlist=modifier&selgrlist=possession&selgrlist=possessor&selgrlist=adj_comp&selgrlist=adj_comp_of&selgrlist=np_adj_comp&selgrlist=np_adj_comp_of&selgrlist=particle&selgrlist=part_intrans&selgrlist=part_trans&selgrlist=pp_%25s&selgrlist=pp_obj_%25s&selgrlist=part_%25s_obj&selgrlist=np_np&selgrlist=np_pp&selgrlist=np_adv&selgrlist=np_sfin&selgrlist=np_VPbare&selgrlist=np_VPing&selgrlist=np_VPto&selgrlist=part_pp&selgrlist=prep_ing&selgrlist=prep_Sing&selgrlist=prep_wh&selgrlist=quote&selgrlist=Sbare&selgrlist=Scond&selgrlist=Sfin&selgrlist=Sforto&selgrlist=Sing&selgrlist=Swh&selgrlist=Swhether&selgrlist=VPto&selgrlist=VPing&selgrlist=there%2B&selgrlist=it%2B&selgrlist=poss&selgrlist=reflexive&selgrlist=passive link] shows a Word Sketch for the noun ''challenge''. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsketch?corpname=preloaded%2Faclarc&lemma=challenge&lpos=-n&minfreq=auto&minscore=0.0&maxitems=25&sort_ws_columns=s&tbl_template=none&tbl_no_examples=6&clustercolls=0&structured=0&structured=1&minsim=0.15&selgrlist=and%2For&selgrlist=object&selgrlist=object_of&selgrlist=subject&selgrlist=subject_of&selgrlist=adj_subject_of&selgrlist=adj_subject&selgrlist=predicate_of&selgrlist=predicate&selgrlist=pro_object&selgrlist=pro_subject&selgrlist=modifier&selgrlist=modifies&selgrlist=possessed&selgrlist=possessor&selgrlist=pro_possessor&selgrlist=wh_comp&selgrlist=infin_comp&selgrlist=ing_comp&selgrlist=passive&selgrlist=reflexive&selgrlist=it%2B&selgrlist=pp_%25s&selgrlist=np_adj_comp&selgrlist=np_adj_comp_of&selgrlist=adj_comp&selgrlist=adj_comp_of&selgrlist=part_intrans&selgrlist=part_trans&selgrlist=part_%25s_obj Alternative link] for ACL ARC.)<br />
<br />
Each column show the words that typically combine with ''challenge'' in a particular grammatical relations (or "gramrels"). Most of these gramrels are self-explanatory. For example, "object_of" lists - in order of statistical significance rather than raw frequency - the verbs that most typically occupy the verb slot in cases where ''challenge'' is the object of a verb. Most of the data is lexicographically relevant, though one might query the adjectival modifier ''larval'': it turns out that ''larval challenge'' is a technical term used in parasitology, discussed in a BNC document.<br />
<br />
You can at any time switch between Concordance mode and Word Sketch mode, and this is a useful way of getting more information about a particular word combination. Thus, if you want to look at examples of "''pose'' + ''challenge''" (where ''challenge'' is the direct object of ''pose''), simply click on the number next to ''pose'' in the "object_of" list (__92__) and you will be taken directly to a concordance showing all instances of this combination.<br />
<br />
== 6. The Thesaurus function == #distributionalthesaurusid<br />
The software checks to see which words occur with the same collocates as other words, and on the basis of this data it generates a "distributional thesaurus". A distributional thesaurus is an automatically produced "thesaurus" which finds words that tend to occur in similar contexts as the target word. It is __not__ a man made thesaurus of synonyms. The thesaurus function lists, for any given adjective, noun or verb, the other words ''most similar'' to it in in terms of grammatical and collocational behaviour.<br />
<br />
Click on the '''Thesaurus''' link on the left hand side main (top) menu and then input the word with PoS that you are interested in. <br />
<br />
For help on the advanced options see [wiki:SkE/Help/PageSpecificHelp/Thesaurus the thesaurus help page].<br />
<br />
== 7. The Sketch Difference function == #sketchdiffid<br />
Sketch Difference is a neat way of comparing two very similar words: it shows those patterns and combinations that the two items have in common, and also those patterns and combinations that are more typical of, or unique to, one word rather than the other. You can also use the function to compare the same lemma in two different parts of the corpus, or to compare two different word forms e.g. ''men'' and ''man''. Click on any word in a Thesaurus entry for a word, and you will be taken straight to a screen showing the Sketch Difference between the two words. Alternatively, you can click on '''Sketch-Diff''' on the left hand side panel and this will take you to the word sketch difference entry form which gives you more options.<br />
<br />
Suppose you want to compare ''clever '' and ''intelligent''. In the thesaurus entry for ''clever'', ''intelligent '' comes top of the list: it is statistically the most similar word in terms of shared contexts of occurrence. Click on ''intelligent'' and you are taken to a new screen which is in three main parts: the first part shows "Common Patterns" (those combinations where ''clever'' and ''intelligent'' behave quite similarly), the second and third parts show "clever only patterns" and "intelligent only patterns". The screen looks like this [http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Fbnc2&lemma=clever&lpos=-j&usesubcorp=;lemma2=intelligent click here]. ([http://the.sketchengine.co.uk/bonito/run.cgi/wsdiff?corpname=preloaded%2Faclarc&lemma=clever&lpos=-j&diff_by=lemma&lemma2=intelligent Alternative link] for ACL ARC.) <br />
<br />
In the "Common Patterns" part, there are four numbers next to each collocate. The first two indicate the frequency of co-occurrence with the first and second lemma, the last two show the salience scores for the collocate with both lemmas. All collocates are sorted according to maximum of the two salience scores and coloured according to difference between the scores.<br />
<br />
Try this out, and look at the difference in the "and/or" lists: people can be "intelligent and articulate/thoughtful/sensitive" etc, but they are often "clever and devious/cunning/brave". <br />
<br />
For more information on the other options see [wiki:SkE/Help/PageSpecificHelp/SketchDiff the Word Sketch Difference help]<br />
<br />
== 8. The Search function ==<br />
<br />
From any screen you can do a "simple" '''Search''' in any corpus by using the field and drop down list in the horizontal panel which appears just beneath the very top bar in which you can search the Help documentation. This search function provides a short cut to a simple concordance<br />
<br />
== 9. Other functions ==<br />
<br />
For an explanation of other functions in the left hand side margin you can click the help links marked with a '''?'''<br />
<br />
----<br />
Click [wiki:WikiStart here] for the Start Page for Sketch Engine Documentation.</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=User:Sivareddy&diff=9332User:Sivareddy2012-05-11T17:43:40Z<p>Sivareddy: Page describing all my softwares</p>
<hr />
<div>Name: Siva Reddy<br />
<br />
Webpage: http://sivareddy.in<br />
<br />
CV: http://sivareddy.in/cv_siva.pdf<br />
<br />
Research Interests: Lexical Semantics, Semantic Composition, Multiwords, Machine Learning, Word Sense Disambiguation/Induction, Lexical Acquisition, Web Corpora, Web as a Resource for NLP problems, Cross Language Resources, Syntactic Parsing, Question Answering Inference<br />
<br />
Keywords: [[Polysemy]], [[Compositionality]], [[Semantic Composition]], [[Domain WSD]], [[Vector Space Models]], [[Semantics]], IIIT Hyderabad, York, Lexical Computing Ltd., [[Sketch Engine]], [[Resources]], [[POS Taggers]], [[Morphological Analyzers]]<br />
<br />
Please find some of the resources developed by me.<br />
<br />
== Compound Noun Compositionality Dataset ==<br />
<br />
[http://sivareddy.in/papers/files/ijcnlp_compositionality_data.tgz '''Compositionality Dataset'''] described in [http://sivareddy.in/papers/ijcnlp2011empirical.pdf Reddy, McCarthy and Manandhar (2011, IJCNLP)]. [http://dianamccarthy.co.uk/downloads.html Alternate download link] from [http://dianamccarthy.co.uk/ Diana McCarthy]<br />
<br />
== POS Taggers, Corpora, Lemmatizers, Morph Analyzers for Indian Languages ==<br />
<br />
Most of these tools are developed by the methods described in [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Reddy and Sharoff (2011, CLIA @ IJCNLP)]. Some of the taggers are built using cross-lingual resources and some using mono-lingual resources. Please read corresponding README's of each tool for additional information. This work is supported by [http://sketchengine.co.uk Sketch Engine] and [http://corpus.leeds.ac.uk/it/ Intellitext project]. If you need resources for any other Indian languages, please contact me.<br />
<br />
=== Kannada Tools ===<br />
<br />
[http://sivareddy.in/papers/files/kannada-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/kannada.sample.out.txt Sample Output of the tagger] For the complete corpus described in the paper, please contact me. [http://corpus.leeds.ac.uk/tools/ Alternate download link] from [http://www.comp.leeds.ac.uk/ssharoff/ Serge Sharoff]<br />
<br />
=== Telugu Tools ===<br />
<br />
[http://sivareddy.in/papers/files/telugu-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/telugu.sample.out.txt Sample Output of the tagger]<br />
<br />
=== Hindi Tools ===<br />
<br />
[http://sivareddy.in/papers/files/hindi-pos-tagger-2.0.tgz Download v2.0] [http://sivareddy.in/papers/files/hindi.sample.out.txt Sample Output of the tagger] [#apertium-indonesian-malaysian ]<br />
<br />
== Indonesian and Malay morphological analyzer, part-of-speech (POS) tagger, Machine Translation System ==<br />
<br />
With support from [http://sketchengine.co.uk Sketch Engine], I have made few contributions to the [http://wiki.apertium.org/wiki/Main_Page Apertium] Indonesian-Malay language pair. All the tools can be downloaded from svn repository https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms/ To download use the command "svn co https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms/" <br /></div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Hindi&diff=9156Resources for Hindi2012-01-16T18:39:56Z<p>Sivareddy: Adding a new POS tagger, Shallow parser. Future: Article Structure needs to be edited. Confusing</p>
<hr />
<div>Hindi computing is gaining momentum very fast. thousands of Hindi sites, blogs and portals have come as a result of availability of computing tools and ease of use. Following link has a list of important tools and softwares for Hindi and Devanaagarii:<br />
<br />
*[http://bit.ly/ytAT95 Hindi Computing : Tools and Techniques]<br />
<br />
==POS Tagger, Morphological Analyzer, Lemmatizer, Corpus==<br />
<br />
* [http://sivareddy.in/downloads Download the tagger]<br />
<br />
* [http://sivareddy.in/papers/files/hindi.sample.out.txt Sample output of the tagger]<br />
<br />
The tagger and its related files are distributed under GNU GPL license. Corpus is licensed.<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://www.aclweb.org/anthology-new/W/W11/W11-3603.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Morphological analysis==<br />
<br />
===Free software===<br />
<br />
* [http://apertium.svn.sourceforge.net/svnroot/apertium/trunk/incubator/apertium-hi-ur.hi.dix Hindi analyser] for [[lttoolbox]] (~29,385 lemmata) -- GPL (by the University of Hyderabad &mdash; converted from the Anusaaraka analyser)<br />
<br />
==Machine translation==<br />
<br />
===Free software===<br />
<br />
* [http://ltrc.iiit.net/~anusaaraka/ Anusaaraka] Hindi&mdash;English and others.<br />
<br />
==Shallow Parser==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Hindi Shallow parser]<br />
<br />
Keywords: Hindi, Part of Speech tagger, Lemmatizer, Morph Analyzer, Corpus<br />
<br />
[[Category:Resources by language|Hindi]]<br />
[[Category: Part of Speech tagger]]<br />
[[Category: Lemmatizer]]<br />
[[Category: Morph Analyser]]<br />
[[Category: Corpus]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Telugu&diff=9149Resources for Telugu2012-01-16T11:32:08Z<p>Sivareddy: </p>
<hr />
<div>==Telugu POS tagger, Morph analyzer, Lemmatizer, Corpus==<br />
<br />
[http://sivareddy.in/downloads Download]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Other resources==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Telugu Shallow parser]<br />
<br />
<br />
Keywords: Telugu, Part of Speech tagger, Lemmatizer, Morph Analyser, Corpus<br />
<br />
[[Category: Telugu]]<br />
[[Category: Part of Speech tagger]]<br />
[[Category: Lemmatizer]]<br />
[[Category: Morph Analyser]]<br />
[[Category: Corpus]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Telugu&diff=9148Resources for Telugu2012-01-16T11:07:35Z<p>Sivareddy: </p>
<hr />
<div>==Telugu POS tagger, Morph analyzer, Corpus==<br />
<br />
[http://sivareddy.in/downloads Download]. [http://corpus.leeds.ac.uk/tools/ Alternate source]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Other resources==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Telugu Shallow parser]<br />
<br />
<br />
Keywords: Telugu, Part of Speech tagger, Lemmatizer, Morph Analyser, Corpus<br />
<br />
[[Category: Telugu]]<br />
[[Category: Part of Speech tagger]]<br />
[[Category: Lemmatizer]]<br />
[[Category: Morph Analyser]]<br />
[[Category: Corpus]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Telugu&diff=9147Resources for Telugu2012-01-16T11:05:22Z<p>Sivareddy: Created page with "==Telugu POS tagger, Morph analyzer, Corpus== [http://sivareddy.in/downloads Download]. [http://corpus.leeds.ac.uk/tools/ Alternate source] <b>Related Publication:</b> Siva Red..."</p>
<hr />
<div>==Telugu POS tagger, Morph analyzer, Corpus==<br />
<br />
[http://sivareddy.in/downloads Download]. [http://corpus.leeds.ac.uk/tools/ Alternate source]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Other resources==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Telugu Shallow parser]<br />
<br />
<br />
[[Category: Telugu]]<br />
[[Category: Part of Speech tagger]]<br />
[[Category: Lemmatizer]]<br />
[[Category: Morph Analyser]]<br />
[[Category: Corpus]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=List_of_resources_by_language&diff=9146List of resources by language2012-01-16T10:59:50Z<p>Sivareddy: </p>
<hr />
<div>List of pages which give links and commentary on computational resources by language.<br />
<br />
Quick Links:<br />
<br />
* [[Resources for English]]<br />
* [[Multilingual resources|Resources for Multilingual Applications]]<br />
<br />
<br />
==A==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Albanian]]<br />
* [[Resources for Amharic]]<br />
* [[Resources for Arabic]]<br />
* [[Resources for Afrikaans]]<br />
<br />
==B==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Basque]]<br />
* [[Resources for Bulgarian]]<br />
* [[Resources for Breton]]<br />
<br />
==C==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Catalan]]<br />
* [[Resources for Chinese]]<br />
* [[Resources for Croatian]] (see also [[Resources for Serbian]], [[Resources for Bosnian]], [[Resources for Serbo-Croatian]])<br />
* [[Resources for Czech]]<br />
<br />
==D==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Danish]]<br />
* [[Resources for Dutch]]<br />
<br />
==E==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for English]]<br />
* [[Resources for Estonian]]<br />
<br />
==F==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Faroese]]<br />
* [[Resources for Finnish]]<br />
* [[Resources for French]]<br />
<br />
==G==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Galician]]<br />
* [[Resources for Georgian]]<br />
* [[Resources for German]]<br />
* [[Resources for Greek]]<br />
* [[Resources for Greenlandic]]<br />
<br />
==H==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Haitian]]<br />
* [[Resources for Hebrew]]<br />
* [[Resources for Hindi]]<br />
* [[Resources for Hungarian]]<br />
<br />
==I==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Icelandic]]<br />
* [[Resources for Indonesian]]<br />
* [[Resources for Iñupiaq]]<br />
* [[Resources for Iranian]]<br />
* [[Resources for Italian]]<br />
* [[Resources for Irish]]<br />
<br />
==J==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Japanese]]<br />
<br />
==K==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Kannada]]<br />
* [[Resources for Korean]]<br />
* [[Resources for Komi]]<br />
* [[Resources for Kurdish]]<br />
<br />
==L==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Lithuanian]]<br />
<br />
==M==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Macedonian]]<br />
* [[Resources for Malay]]<br />
* [[Resources for Maltese]]<br />
* [[Resources for Montenegrin]]<br />
* [[Multilingual resources|Resources for Multilingual Applications]]<br />
<br />
==N==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Norwegian]]<br />
* [[Resources for Navajo]]<br />
<br />
==O==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Occitan]]<br />
<br />
==P==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Pashto]]<br />
* [[Resources for Persian]]<br />
* [[Resources for Polish]]<br />
* [[Resources for Portugese]]<br />
* [[Resources for Punjabi]]<br />
<br />
==Q==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Quechua]]<br />
<br />
==R==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Romanian]]<br />
* [[Resources for Russian]]<br />
<br />
==S==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Sámi]]<br />
* [[Resources for Sanskrit]]<br />
* [[Resources for Slovak]]<br />
* [[Resources for Slovenian]]<br />
* [[Resources for Sorbian]]<br />
* [[Resources for Spanish]]<br />
* [[Resources for Swahili]]<br />
* [[Resources for Swedish]]<br />
<br />
==T==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Tajik]]<br />
* [[Resources for Turkish]]<br />
* [[Resources for Tigrinya]]<br />
* [[Resources for Telugu]]<br />
<br />
==U==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Ukrainian]]<br />
* [[Resources for Urdu]]<br />
<br />
==V==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Vietnamese]]<br />
<br />
==W==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Welsh]]<br />
<br />
==Z==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Zulu]]<br />
<br />
==See also==<br />
<br />
* [[Resources for African languages]]<br />
<br />
[[Category:Resources by language|*]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Kannada&diff=9074Resources for Kannada2011-11-24T09:43:44Z<p>Sivareddy: </p>
<hr />
<div>==Kannada POS tagger, Morph analyzer, Corpus==<br />
<br />
[http://sivareddy.in/downloads Download]. [http://corpus.leeds.ac.uk/tools/ Alternate source]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Other resources==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php Kannada Shallow parser]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Kannada&diff=9073Resources for Kannada2011-11-24T09:43:25Z<p>Sivareddy: Updates and new download links</p>
<hr />
<div>==Kannada POS tagger, Morph analyzer, Corpus==<br />
<br />
[http://sivareddy.in/downloads Download]. [http://corpus.leeds.ac.uk/tools/ Alternate source]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]<br />
<br />
==Other resources==<br />
<br />
[http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php] Kannada Shallow parser</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Kannada&diff=9072Resources for Kannada2011-11-24T09:41:40Z<p>Sivareddy: </p>
<hr />
<div>==Kannada POS tagger, Morph anaylzer, Corpus==<br />
<br />
[http://sivareddy.in/downloads Download]. [http://corpus.leeds.ac.uk/tools/ Alternate source]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=People&diff=9062People2011-11-06T14:01:54Z<p>Sivareddy: </p>
<hr />
<div>This is a list of homepages of researchers in Computational Linguistics, in the form '''last name, first name - affiliation'''. <br />
<br />
See also [[Academic genealogy]], the genealogy of people with academic degrees, based on graduate supervisors being 'parents' and their graduate students being 'children'.<br />
<br />
== A ==<br />
<br />
*[http://littera.deusto.es/prof/abaitua Abaitua, Joseba] - Universidad de Deusto<br />
*[http://tony.abou-assaleh.net Abou-Assaleh, Tony] - Dalhousie University<br />
*[http://www-personal.umich.edu/~ladamic/ Adamic, Lada] - University of Michigan<br />
*[http://www.cond.org/ Adar, Eytan] - University of Washington<br />
*[http://www.dfki.de/~janal/ Alexandersson, Jan] - German Research Center for Artificial Intelligence<br />
*[http://www.ics.uci.edu/~boris Aleksandrovsky, Boris] UC Irvine<br />
*[http://www-scf.usc.edu/~alcazar/ Alcázar, Asier] - University of Southern California<br />
*[http://alfonseca.org/ Alfonseca, Enrique] - Google<br />
*[http://ixa.si.ehu.es/Ixa/Argitalpenak/kidearen_argitalpenak?kidea=1000808989 Alegria, Iñaki] - University of the Basque Country<br />
*[http://www.dfki.de/~janal/ Alexandersson, Jan] German Research Center for Artificial Intelligence<br />
*[http://www.cs.rochester.edu/u/james/ Allen, James] - University of Rochester<br />
*[http://www.dc.fi.udc.es/~alonso/ Alonso, Miguel A.]<br />
*[http://www.linguist.jussieu.fr/~amsili/ Amsili, Pascal] - University of Paris 7 - Denis Diderot<br />
*[http://www.aueb.gr/users/ion/ Androutsopoulos, Ion] - Athens University of Economics and Business<br />
*[http://clwww.essex.ac.uk/~doug/ Arnold, Doug] Univ. of Essex<br />
*[http://www.ai.sri.com/~appelt/ Appelt, Doug ] SRI International<br />
*[http://korpus.dsl.dk/staff/ja/ Asmussen, Jörg] - DSL - Society for Danish Language and Literature, Copenhagen<br />
*[http://www.carleton.ca/~asudeh/ Asudeh, Ash] - Carleton University <br />
*[http://www.coli.uni-sb.de/~tania/ Avgustinova, Tania] - Universität des Saarlandes<br />
<br />
== B ==<br />
<br />
*[http://www.cs.cmu.edu/~klb Baker, Kathryn] - Carnegie Mellon University<br />
*[http://comp.ling.utexas.edu/jbaldrid/ Baldridge, Jason] - University of Texas at Austin<br />
*[http://www.cs.mu.oz.au/~tim/ Baldwin, Timothy] - University of Melbourne<br />
*[http://www.georgetown.edu/cball/cball.html Ball, Catherine] - Georgetown University<br />
*[http://www.cs.cmu.edu/~banerjee Banerjee, Satanjeev] - Carnegie Mellon University<br />
*[http://www.lsi.upc.es/~batalla Batalla,Jordi Atserias] - UPC, Spain<br />
*[http://www5.informatik.uni-erlangen.de/Personen/batliner/ Batliner, Anton] - Friedrich-Alexander-Universität Erlangen-N&uuml;rnberg<br />
*[http://www.dfki.de/~becker Becker, Tilman] - DFKI Saarbruecken, Germany<br />
*[http://faculty.washington.edu/ebender Bender, Emily] - University of Washington<br />
*[http://homepages.infoseek.com/~corpuslinguistics/homepage.html Berber,Tony] Sardinha<br />
*[http://richard.bergmair.eu/ Bergmair, Richard] University of Cambridge<br />
*[http://wortschatz.uni-leipzig.de/~cbiemann/ Biemann, Chris] - University of Leipzig, Germany<br />
*[http://www.dai.ed.ac.uk/students/kimb Binsted, Kim] University of Edinburgh<br />
*[http://www.cs.mu.oz.au/~sb/ Bird, Steven] - University of Melbourne<br />
*[http://seneca.uab.es/filfrirom/Blanco.html Blanco, Xavier] - Autonomous University of Barcelona<br />
*[http://www.pdg.cnb.uam.es/blaschke/personalPage.html Blaschke, Christian]<br />
*[http://www.dcs.shef.ac.uk/~kalina/ Boncheva, Kalina] Univ. of Sheffield]<br />
*[http://www.dcs.shef.ac.uk/~kalina/ Bontcheva, Kalina] - Univ. of Sheffield<br />
*[http://www3.ntu.edu.sg/home/fcbond/ Bond, Francis] - Nanyang Technological University, Singapore<br />
*[http://homepages.inf.ed.ac.uk/jbos/ Bos, Johan] - University of Groningen<br />
*[http://www.iro.umontreal.ca/~boufaden/ Boufaden, Narjès] - University of Montreal<br />
*[http://www.let.rug.nl/~gosse Bouma, Gosse] - University of Groningen<br />
*[http://www.di.fc.ul.pt/~ahb/ Branco, Antonio] - University of Lisbon<br />
*[http://www.karlbranting.net Branting, Karl]<br />
*[http://coli.uni-sb.de/~thorsten Brants, Thorsten] - University of Saarland<br />
*[http://www.coli.uni-sb.de/~brawer Brawer, Sascha] - University of the Saarland<br />
*[http://www.cs.cornell.edu/~ebreck Breck, Eric] - Cornell University<br />
*[http://clwww.essex.ac.uk/~andrewb/ Bredenkamp, Andrew]<br />
*[http://www.csse.monash.edu.au/~jwb/ Breen, Jim] - Monash University<br />
*[http://www.cog.jhu.edu/faculty/brent.html Brent,Michael R.] Johns Hopkins University<br />
*[http://www.informatik.uni-leipzig.de/~brewka/ Brewka] - Gerhard, University of Leipzig<br />
*[http://www.xsoft.com/ Breyman, Clark] Xerox Linguistic Technologies<br />
*[http://research.microsoft.com/%7Ebrill/ Brill, Eric] - Microsoft Research<br />
*[http://www.cl.cam.ac.uk/users/ejb/ Briscoe, Ted] - University of Cambridge<br />
*[http://www.dfki.de/~paulb Buitelaar, Paul] - DFKI<br />
*[http://www.cs.utexas.edu/users/razvan/ Bunescu, Razvan] - University of Texas at Austin<br />
<br />
== C ==<br />
<br />
*[http://www.hinocatv.ne.jp/~price/ Caldwell, Price] - Meisei University<br />
*[http://www.acs.ilstu.edu/faculty/mecalif/calif.htm Califf,Mary Elaine] - Illinois State University<br />
*[http://ilk.uvt.nl/~sander/ Canisius, Sander] - Tilburg University<br />
*[http://www.cis.upenn.edu/~cliff-group/94/carberry.html Carberry, Sandra] - Univ. of Delaware, Univ. of Pennsylvania<br />
*[http://www.cs.cornell.edu/Info/Faculty/Claire_Cardie.html Cardie, Claire] - Cornell University<br />
*[http://www.cogs.susx.ac.uk/lab/nlp/carroll/carroll.html Carroll, John] - University of Sussex<br />
*[http://jones.ling.indiana.edu/~dcavar Cavar, Damir] - Indiana University, Bloomington<br />
*[http://tantek.com/map.html Celik, Tantek] - Technorati<br />
*[http://cer.freeshell.org Cer, Daniel] - University of Colorado at Boulder<br />
*[http://nlp.changwon.ac.kr/~jcha/ Cha, Jeongwon] - Changwon National University<br />
*[http://www.cs.uleth.ca/~chali Chali, Yllias] - University of Lethbridge<br />
*[http://www.cs.brown.edu/people/ec/home.html Charniak, Eugene] - Brown University<br />
*[http://iit-iti.nrc-cnrc.gc.ca/personnel/chen_boxing_e.html Chen, Boxing] - National Research Council<br />
*[http://www.ciscl.unisi.it/persone/chesi.htm Chesi, Cristiano] - CISCL, University of Siena<br />
*[http://www.isi.edu/~chiang Chiang, David] - USC Information Sciences Institute<br />
*[http://www.alphabit.net/Docente/docente_eng.htm Chiari, Isabella] - University "La Sapienza" of Rome<br />
*[http://korterm.kaist.ac.kr/kschoi/ Choi, Key-Sun] - Korea Advanced Institute of Science and Technology<br />
*[http://web.mit.edu/afs/athena.mit.edu/org/l/linguistics/www/chomsky.home.html Chomsky, Noam] - MIT<br />
*[http://research.microsoft.com/users/church/ Church, Kenneth] - Microsoft Research<br />
*[http://www.dcs.shef.ac.uk/~fabio/ Ciravegna, Fabio] - University of Sheffield<br />
*[http://web.comlab.ox.ac.uk/oucl/work/stephen.clark/ Clark, Stephen] - University of Oxford<br />
*[http://compbio.uchsc.edu/Hunter_lab/Cohen Cohen, Kevin Bretonnel] - U. Colorado School of Medicine<br />
*[http://people.csail.mit.edu/u/m/mcollins/public_html/ Collins, Michael] - MIT Computer Science and Artificial Intelligence Laboratory<br />
*[http://www.cl.cam.ac.uk/users/aac10/ Copestake, Ann] - University of Cambridge<br />
*[http://lands.let.kun.nl/TSpublic/coppen Coppen, Peter-Arno] - University of Nijmegen, The Netherlands<br />
*[http://plg.uwaterloo.ca/~gvcormac/ Cormack, Gordon] - University of Waterloo<br />
*[http://www.psych.qub.ac.uk/staff/teaching/cowie/index.aspx Cowie, Roddy] - Queen's University, Belfast<br />
*[http://www.biostat.wisc.edu/~craven/ Craven, Mark] - University of Wisconsin<br />
*[http://www2.ulster.ac.uk/staff/n.creaney.html Creaney, Norman] - University of Ulster<br />
*[http://www.dia.uniroma3.it/~crescenz/ Crescenzi, Valter] - Università Roma Tre<br />
*[http://thor.info.uaic.ro/~dcristea/ Cristea, Dan] - University of Iasi<br />
*[http://www.harlequin.com/ Crowe, Jeremy] - Harlequin Ltd.<br />
*[http://www.dcs.shef.ac.uk/~hamish Cunningham, Hamish] - University of Sheffield<br />
*[http://www-users.cs.york.ac.uk/~jc/ Cussens, James] - University of York<br />
<br />
== D ==<br />
*[http://www.cs.biu.ac.il/~dagan/ Dagan, Ido] - Bar Ilan University, Israel<br />
*[http://conversational-technologies.com Dahl, Deborah] - Conversational Technologies<br />
*[http://stl.recherche.univ-lille3.fr/sitespersonnels/dal/index.html Dal, Georgette] - Universite de Lille<br />
*[http://www.ics.mq.edu.au/~rdale Dale, Robert] - Centre for Language Technology, Macquarie University<br />
*[http://www.cs.utah.edu/~hal/ Daumé III, Hal] - University of Utah<br />
*[http://davies-linguistics.byu.edu Davies, Mark] - Brigham Young University<br />
*[http://cs.haifa.ac.il/~edaya Daya, Ezra] - NICE Systems Ltd.<br />
*[http://www.csi.uottawa.ca/~delannoy Delannoy, Jean-Francois] - University of Ottawa<br />
*[http://www.uqtr.uquebec.ca/~delisle/index.html Delisle, Sylvain] UQTR<br />
*[http://comp.ling.utexas.edu/denis Denis, Pascal] - University of Texas at Austin<br />
*[http://www.math.bas.bg/~iad/ Derzhanski, Ivan] - Bulgarian Academy of Sciences<br />
*[http://www.ling.ohio-state.edu/~dm/ Detmar Meurers, Walt] - The Ohio State University Linguistics Dept.<br />
*[http://www.limsi.fr/Individu/devil/ Devillers, Laurence] - LIMSI<br />
*[http://ixa.si.ehu.es/Ixa/Argitalpenak/kidearen_argitalpenak?kidea=1000808994 Díaz de Ilarraza, Arantza] - University of Basque Country<br />
*[http://www.cs.umd.edu/users/bonnie/ Dorr, Bonnie] - University of Maryland<br />
*[http://www.nyu.edu/pages/linguistics/doughert.html Dougherty, Ray] - New York University<br />
*[http://www.ai.sri.com/~dowding Dowding, John] - SRI<br />
*[http://www.pcug.org.au/~jdowling/ Dowling, Jason] PC Users Group ACT Inc., Canberra, Australia<br />
<br />
== E ==<br />
<br />
*[http://www.uni-bielefeld.de/lili/personen/cebert/ Ebert, Christian] - University of Bielefeld<br />
*[http://www.ims.uni-stuttgart.de/~eckle/ Eckle-Kohler, Judith]<br />
*[http://www.philipedmonds.com/ Edmonds, Philip] - University of Toronto<br />
*[http://cs.jhu.edu/~jason Eisner, Jason] - Johns Hopkins University<br />
*[http://www.cs.bgu.ac.il/~elhadad/ Elhadad, Michael] - Ben-Gurion University of the Negev<br />
*[http://www.cogsci.ed.ac.uk/~marke/ Ellison, T. Mark] - University of Edinburgh<br />
*[http://www.ik.fh-hannover.de/ik/person/ben/ben.htm Endres-Niggemeyer, Brigitte] FH Hannover<br />
*[http://www.sciences.univ-nantes.fr/info/perso/permanents/enguehard/ Enguehard, Chantal] - Laboratoire d'Informatique de Nantes Atlantique<br />
*[http://coli.uni-sb.de/~erbach/ Erbach, Gregor] - Universität des Saarlandes<br />
*[http://nl.ijs.si/et/ Erjavec, Tomaz]<br />
*[http://comp.ling.utexas.edu/erk/ Erk, Katrin] - University of Texas at Austin<br />
*[http://www.cogsci.uni-osnabrueck.de/~severt/ Evert, Stefan] - University of Osnabrück<br />
<br />
== F ==<br />
<br />
*[http://slt.wcl.ee.upatras.gr/Fakotakis/personal.htm Fakotakis, Nikos] - University of Patras<br />
*[http://www.phon.ucl.ac.uk/home/alex/home.htm Fang, Alex Chengyu] - University College London<br />
*[http://www.purl.org/net/fa Feldman, Anna] - Montclair State University<br />
*[http://wordnet.princeton.edu/~fellbaum/ Fellbaum, Christiane] - Princeton University<br />
*[http://ling.cuc.edu.cn/htliu/feng/feng.htm Feng, Zhiwei] - IAL of China<br />
*[http://staff.science.uva.nl/~raquel/ Fernandez, Raquel] - ILLC, University of Amsterdam<br />
*[http://www.cs.umbc.edu/~finin/ Finin, Tim] - University of Maryland<br />
*[http://lingo.stanford.edu/dan/ Flickinger, Dan] - CSLI, Stanford University<br />
*[http://www.dlsi.ua.es/~mlf/ Mikel Forcada] - Universitat d'Alacant<br />
*[http://www.cse.ohio-state.edu/~fosler Fosler-Lussier, Eric] - The Ohio State University<br />
*[http://www.coli.uni-saarland.de/~fouvry/ Fouvry, Frederik]<br />
*[http://www.cs.brown.edu/people/hjf/ Fox, Heidi] - Brown University, Metacarta<br />
*[http://www.cs.technion.ac.il/~francez Francez, Nissim] - Technion, Israel<br />
*[http://www.cs.cmu.edu/~ref/ Frederking, Robert] - Carnegie-Mellon University<br />
*[http://www.ee.ust.hk/~pascale/ Fung, Pascale] - Hong Kong University of Science and Technology<br />
<br />
== G ==<br />
<br />
*[http://www.cs.technion.ac.il/~gabr Gabrilovich, Evgeniy]<br />
*[http://www.dcs.shef.ac.uk/~robertg/ Gaizauskas, Rob] - University of Sheffield<br />
*[http://www.sics.se/~gamback/ Gamback, Bjorn] - Swedish Institute of Computer Science<br />
*[http://www.dai.ed.ac.uk/students/narcisbg Gardella, Narcis Bassols] Univ. of Edinburgh<br />
*[http://www.coli.uni-sb.de/~claire/ Gardent, Claire] Universit&auml;t des Saarlandes<br />
*[http://www.gelbukh.com/ Gelbukh, Alexander] - CIC-IPN<br />
*[http://www.isi.edu/natural-language/people/germann/ Germann, Ulrich] - ISI<br />
*[https://netfiles.uiuc.edu/girju/index.html Girju, Roxana] - University of Illinois, Urbana-Champaign<br />
*[http://tcc.itc.it/people/giuliano.html Giuliano, Claudio] - ITC-irst<br />
*[http://www.uni-salzburg.at/portal/page?_pageid=425,405845&_dad=portal&_schema=PORTAL Goebl, Hans] - Univeristät Salzburg<br />
*[http://www.cs.ucf.edu/~gomez Gomez, Fernando] ucf<br />
*[http://www.esi.uem.es/~jmgomez Gomez-Hidalgo, Jose-Maria] - UEM<br />
*[http://www.linguistics.ucsb.edu/faculty/stgries/ Gries, Stefan Th.] - UCSB<br />
*[http://cs.nyu.edu/cs/faculty/grishman/ Grishman, Ralph] - New York University<br />
*[http://das-www.harvard.edu/users/faculty/Barbara_Grosz/Barbara_Grosz.html Grosz, Barbara] - Harvard University<br />
*[http://www-ksl.stanford.edu/people/gruber/ Gruber, Tom] - Stanford University<br />
*[http://www.cs.duke.edu/~cig Guinn, Curry I.] - Duke U.<br />
*[http://www.ukp.tu-darmstadt.de/ Gurevych, Iryna] - Darmstadt University of Technology<br />
*[http://www.cs.bilkent.edu.tr/~guvenir/guvenir.html Guvenir, Altay] - Bilkent University<br />
<br />
== H ==<br />
<br />
*[http://www.swan.ac.uk/french/web-content/staff/p-ten-hacken.html Hacken, Pius ten] - Swansea University<br />
*[http://www.coling.uni-freiburg.de/~hahn/hahn.html Hahn, Udo] - University of Freiburg<br />
*[http://ufal.mff.cuni.cz/~hajic Hajič, Jan] - Charles University in Prague<br />
*[http://www.comp.nus.edu.sg/~cuihang Hang, Cui] - National University of Singapore<br />
*[http://www.coli.uni-sb.de/~hansen Hansen-Schirra, Silvia] - Universität des Saarlandes<br />
*[http://renoir.vill.edu/faculty/hardt/html/home.html Hardt, Daniel] Villanova University<br />
*[http://128.147.244.54/dbmi/profile.cfm?ID=23751 Harkema, Henk] - University of Pittsburgh<br />
*[http://pi7.fernuni-hagen.de/hartrumpf/ Hartrumpf, Sven] - University of Hagen, Germany<br />
*[http://www.cis.udel.edu/~harvey/ Harvey, Terry]<br />
*[http://www.linguistik.uni-erlangen.de/~rrh/ Hausser, Roland] - University of Erlangen, Germany<br />
*[http://www.sims.berkeley.edu/~hearst Hearst, Marti] - UC Berkeley<br />
*[http://www.cse.ogi.edu/~heeman Heeman, Peter] - OGI<br />
*[http://homepages.inf.ed.ac.uk/jhender6/ Henderson, James] - University of Edinburgh<br />
*[http://www.asp.ogi.edu/~hynek/ Hermansky, Hynek] - Oregon Graduate Institute of Science and Technology<br />
*[http://www.isi.edu/~ulf/ Hermjakob, Ulf] - USC/ISI<br />
*[http://www.esi.uem.es/~jmgomez/ Hidalgo, José María Gómez] - Universidad Europea de Madrid<br />
*[http://www.ifi.unizh.ch/staff/hess.html Hess, Michael] - Univ. of Zurich, Switzerland<br />
*[http://www.cs.toronto.edu/~gh Hirst, Graeme] - University of Toronto<br />
*[http://www.isi.edu/~hobbs/ Jerry Hobbs] - USC/ISI<br />
*[http://www.cs.cmu.edu/~chogan Hogan, Christopher] - Carnegie-Mellon University<br />
*[http://www.isi.edu/natural-language/people/hovy.html Hovy, Eduard] - ISI<br />
*[http://ist-socrates.berkeley.edu/~jcl2/churen.htm Huang, Chu-Ren] - Academica Sinica<br />
*[http://www.cs.ucf.edu/~hull Hull, Richard] - University of Central Florida<br />
*[http://compbio.uchsc.edu/Hunter_lab/Hunter Hunter, Larry] - U. Colorado School of Medicine<br />
*[http://datamining.typepad.com/data_mining/ Hurst, Matthew] - BuzzMetrics<br />
*[http://ourworld.compuserve.com/homepages/WJHutchins/ Hutchins, John]<br />
*[http://www.cs.pitt.edu/~hwa Hwa, Rebecca] - University of Pittsburgh<br />
<br />
== I ==<br />
<br />
== J ==<br />
<br />
*[http://www.cis.upenn.edu/~cliff-group/94/pjacobs.html Jacobs, Paul] - General Electric<br />
*[http://www.stanford.edu/~tiflo Jaeger, T. Flroian] - Stanford University<br />
*[http://ist.psu.edu/faculty_pages/jjansen/ Jansen, Jim] - Penn State<br />
*[http://www.cs.nyu.edu/~hengji Ji, Heng] - New York University<br />
*[http://www.cog.brown.edu/~mj Johnson, Mark] - Brown University<br />
*[http://www.cogsci.ed.ac.uk/~bernie/ Jones, Bernie] University of Edinburgh<br />
*[http://www.ida.liu.se/~arnjo/ Jönsson, Arne] - Linkoping University<br />
<br />
== K ==<br />
*[http://cs.joensuu.fi/~tkakkone Kakkonen, Tuomo] - University of Joensuu<br />
*[http://www.ai.sri.com/~megumi Kameyama, Megumi] - SRI International<br />
*[http://www.comp.nus.edu.sg/~kanmy Kan, Min-Yen] - National University of Singapore<br />
*[http://users.utu.fi/karhumak/ Karhumaki, Juhani] - University of Turku<br />
*[http://www.sics.se/~jussi/ Karlgren, Jussi] - SICS, Sweden<br />
*[http://www2.parc.com/istl/members/karttune/ Karttunen, Lauri]<br />
*[http://elex.amu.edu.pl/ifa/staff/kaszubski.html Kaszubski, Przemys&#322;aw] - Adam Mickiewicz University<br />
*[http://www.cs.utexas.edu/users/rjkate/ Kate, Rohit J.] - University of Texas at Austin<br />
*[http://www-users.cs.york.ac.uk/~kazakov/ Kazakov, Dimitar] - University of York<br />
*[http://homepages.inf.ed.ac.uk/keller/ Keller, Frank] - University of Edinburgh<br />
*[http://www.cs.dal.ca Keselj, Vlado] Dalhousie University<br />
*[http://www.mabidkhan.com/ Khan, Abid] - University of Peshawar, Pakistan<br />
*[http://www.itri.bton.ac.uk/~Adam.Kilgarriff Kilgarriff, Adam] - University of Brighton<br />
*[http://www.cs.wisc.edu/~sklein/sklein.html Klein, Sheldon] - University of Wisconsin<br />
*[http://www.isi.edu/~knight/ Knight, Kevin] - ISI<br />
*[http://www.ims.uni-stuttgart.de/~kobdani/ Kobdani, Hamidreza] - University of Stuttgart<br />
*[http://www.iccs.inf.ed.ac.uk/~pkoehn/ Koehn, Philipp] - University of Edinburgh<br />
*[http://svenska.gu.se/~svedk Kokkinakis, Dimitrios] - Göteborg University<br />
*[http://www.coli.uni-saarland.de/~kordoni/ Kordoni, Valia] - Universität des Saarlandes<br />
*[http://www.kornai.com/ Kornai, Andras]<br />
*[http://www.ling.helsinki.fi/~koskenni/ Koskenniemi, Kimmo] - University of Helsinki<br />
*[http://users.encs.concordia.ca/~kosseim/ Kosseim, Leila] - Concordia University, Montreal<br />
*[http://www.dlsi.ua.es/~zkozareva/ Kozareva, Zornitsa] - University of Alicante<br />
*[http://dis.tpd.tno.nl/mmts/wessel_kraaij.html Kraaij, Wessel] - TNO<br />
*[http://www-sk.let.uu.nl Krauwer, Steven, ELSNET] - Utrecht University<br />
*[http://external.nj.nec.com/homepages/krovetz/ Krovetz, Robert] NEC<br />
*[http://www.peter-kuehnlein.net/ Kuehnlein, Peter] - University of Groningen<br />
*[http://jones.ling.indiana.edu/~skuebler/ Kuebler, Sandra] - Indiana University, Bloomington<br />
*[http://www.cs.ucd.ie/staff/nick/ Kushmerick, Nicholas] - University College, Dublin<br />
<br />
== L ==<br />
<br />
*[http://www.ling.gu.se/~lager/ Lager, Torbjörn] - Göteborg University<br />
*[http://www.ict.csiro.au/staff/Andrew.Lampert/ Lampert, Andrew] - CSIRO ICT Centre / Macquarie University<br />
*[http://www.cs.cmu.edu/~ianlane/ Lane, Ian] - Carnegie Mellon University<br />
*[http://tcc.itc.it/people/lavelli/ Lavelli, Alberto] - ITC-IRST<br />
*[http://www-personal.umich.edu/~jlawler/index.html Lawler, John] - University of Michigan<br />
*[http://nlp.postech.ac.kr/~gblee Lee, Geunbae] - POSTECH<br />
*[http://www.cs.cornell.edu/home/llee Lee, Lillian] - Cornell University<br />
*[http://www.cs.bham.ac.uk/~mgl Lee, Mark] - University of Birmingham<br />
*[http://www.ling.lancs.ac.uk/staff/geoff/geoff.htm Leech, Geoffrey] - Professor LAMEL, Lancaster University, UK<br />
*[http://jochenleidner.com/ Leidner, Jochen L.] - Research Scientist, Thomson Reuters Corporation<br />
*[http://homepages.inf.ed.ac.uk/olemon Lemon, Oliver]<br />
*[http://www.ilc.cnr.it/~lenci/ Lenci, Alessandro] - Università di Pisa<br />
*[http://people.cs.uchicago.edu/~levow/ Levow, Gina-Anne] - University of Chicago<br />
*[http://www.cc.gatech.edu/~baoli/ Li, Baoli] - Georgia Institute of Technology<br />
*[http://www1.i2r.a-star.edu.sg/~hli/ Li, Haizhou] - Institute for Infocomm Research, Singapore<br />
*[http://www.ling.upenn.edu/~myl/ Liberman, Mark] - University of Pennsylvania<br />
*[http://www.isi.edu/~cyl/ Lin, Chin-Yew] USC/ISI<br />
*[http://www.cs.ualberta.ca/~lindek/ Lin, Dekang] - University of Alberta<br />
*[http://htliu.yeah.net/ Liu, Haitao] - Communication University of China<br />
*[http://mtgroup.ict.ac.cn/~liuyang/ Liu, Yang] - Institute of Computing Technology, CAS<br />
*[http://ufal.mff.cuni.cz/~lopatkova Lopatková, Markéta] Charles University in Prague<br />
*[http://terra.di.fct.unl.pt/~gpl/ Lopes, Gabriel] New University of Lisbon<br />
*[http://www.langnat.com/~loupy/index-en.html Loupy, Claude de] - Universite de Paris X Nanterre<br />
*[http://www.personal.psu.edu/xxl13 Lu, Xiaofei] - Pennsylvania State University<br />
<br />
== M ==<br />
<br />
*[http://www.soi.city.ac.uk/~andym/ MacFarlane, Andrew] - City University of London<br />
*[http://www.desilinguist.org Madnani, Nitin] - Educational Testing Service<br />
*[http://www-cs-students.Stanford.EDU/~magerman Magerman, David] - Stanford University<br />
*[http://tcc.itc.it/people/magnini.html Magnini, Bernardo] - ITC-IRST<br />
*[http://www.karacaymalkar.com Malkar, Karacay] - Webportal<br />
*[http://www.rohan.sdsu.edu/~malouf Malouf, Rob] - San Diego State University<br />
*[http://www.sultry.arts.usyd.edu.au/ Manning, Christopher] - University of Sydney<br />
*[http://www.demarcken.org/carl/ de Marcken, Carl] ITA Software<br />
*[http://www.isi.edu/~marcu/ Marcu, Daniel] - USC/ISI<br />
*[http://overstated.net/about Marlow, Cameron] - Yahoo! Research<br />
*[http://www.limsi.fr/Individu/martin/ Martin,Jean-Claude] - LIMSI<br />
*[http://www.yorku.ca/jmason/ Mason, James A.] - York University<br />
*[http://www.ics.mq.edu.au/~mpawel Mazur, Pawel] - Wroclaw University of Technology and Macquarie University<br />
*[http://www.informatics.susx.ac.uk/research/nlp/mccarthy/mccarthy.html McCarthy, Diana] - University of Sussex<br />
*[http://homepages.inf.ed.ac.uk/mmcconvi McConville, Mark] - University of Edinburgh<br />
*[http://alum.mit.edu/www/davidmcdonald/ McDonald, David] - Smart Information Flow Technologies (SIFT)<br />
*[http://www.cs.columbia.edu/~kathy McKeown, Kathy] Columbia University<br />
*[http://www.eecis.udel.edu/~mccoy/ McKoy, Kathy] - University of Delaware<br />
*[http://stp.lingfil.uu.se/~bea Megyesi, B. Beata] - Uppsala University<br />
*[http://cs.nyu.edu/~melamed Melamed, I. Dan] - New York University<br />
*[http://www.latl.unige.ch/personal/paola.html Merlo, Paola] - University of Geneva<br />
*[http://www.ling.ohio-state.edu/~dm/ Meurers, Walt Detmar] OH State Linguistics<br />
*[http://www.csse.uwa.edu.au/~fontor/ Midgley, T. Daniel] - University of Western Australia<br />
*[http://www.cs.unt.edu/~rada Mihalcea, Rada] - University of North Texas<br />
*[http://www.cis.upenn.edu/~elenimi/ Miltsakaki, Eleni] - University of Pennsylvania<br />
*[http://www.ics.mq.edu.au/~mariam Milosavljevic, Maria] - Macquarie University<br />
*[http://coli.uni-sb.de/~mineur Mineur, Anne-Marie] University of the Saarland / Utrecht University<br />
*[http://imaginarycartography.com/work.html Minor, Joshua T.] - Cataphora, Inc.<br />
*[http://staff.science.uva.nl/~gilad/ Mishne, Gilad] - University of Amsterdam<br />
*[http://www.wlv.ac.uk/~le1825/main.html Mitkov, Ruslan] - University of Wolverhampton<br />
*[http://www.let.rug.nl/~begona/ Moirón, Begoña Villada] - University of Groningen<br />
*[http://www.ifi.unizh.ch/~molla/ Molla-Aliod, Diego] - University of Zurich<br />
*[http://www.dcs.qmul.ac.uk/~christof/ Monz, Christof] - University of Amsterdam (ILLC)<br />
*[http://www.cs.utexas.edu/users/mooney/ Mooney, Raymond J.] - University of Texas at Austin<br />
*[http://www.signiform.com/erik/ Mueller, Erik] - IBM Research<br />
*[http://www.xn--stefan-mller-klb.net/ Müler, Stefan] - Universität Bremen<br />
*[http://www.ukp.tu-darmstadt.de/people/mueller/ Müller, Christof] - Darmstadt University of Technology<br />
*[http://www.dlsi.ua.es/eines/membre.cgi?id=eng&nom=rafael&tipus=pdi Muñoz, Rafael] - University of Alicante<br />
*[http://www.puran.info Malik, Abbas] - GETALP - LIG, Université de Grenoble<br />
<br />
== N ==<br />
<br />
*[http://www.cs.utexas.edu/users/ai-lab/people/grad/nahm.html Nahm, Un Yong] - University of Texas, Austin<br />
*[http://www.univ-nancy2.fr/pers/namer/ Namer, Fiammetta] - University of Nancy<br />
*[http://www.lr.pi.titech.ac.jp/~nanno/index.cgi?page=Tomoyuki+NANNO Nanno, Tomoyuki] - Tokyo Institute of Technology<br />
*[http://www.dlsi.ua.es/~borja/ Navarro, Borja] - University of Alicante, Spain<br />
*[http://tcc.itc.it/people/negri.html Negri, Matteo] - ITC-irst<br />
*[http://www.let.rug.nl/~nerbonne Nerbonne, John] - University of Groningen<br />
*[http://cl-www.dfki.uni-sb.de/~neumann Neumann, Guenter] - DFKI, Saarbrücken<br />
*[http://www.comp.nus.edu.sg/~nght Ng, Hwee Tou] - National University of Singapore<br />
*[http://www.hlt.utdallas.edu/~vince Ng, Vincent] - University of Texas at Dallas<br />
*[http://jdpowerwebintelligence.com/ Nicolov, Nicolas] - J.D. Power and Associates, McGraw-Hill<br />
*[http://www.slt.atr.co.jp/~night/ Nightingale, Stephen] - ATR Institute International<br />
*[http://homepages.inf.ed.ac.uk/mnissim/ Nissim, Malvina] - University of Bologna<br />
*[http://www.comp.nus.edu.sg/~niuzheng Niu, Zheng-Yu] - NU Singapore<br />
*[http://w3.msi.vxu.se/~nivre/ Nivre, Joakim] - Växjö University<br />
*[http://www.cs.berkeley.edu/~russell/norvig.html Norvig, Peter]<br />
<br />
== O ==<br />
<br />
*[http://www.ltg.ed.ac.uk/~jon/ Oberlander, Jon] - U. Edinburgh<br />
*[http://people.sabanciuniv.edu/oflazer/ Oflazer, Kemal] - Sabanci University, Istanbul, Turkey<br />
*[http://www.loa-cnr.it/oltramari.html Oltramari, Alessandro] - Laboratory for Applied Ontology, Italian National Research Council<br />
*[http://www.wlv.ac.uk/~in6093/ Orasan, Constantin] - University of Wolverhampton<br />
*[http://www.bultreebank.org/petya/OsenovaPub.html Osenova, Petya] - Bulgarian Academy of Sciences<br />
<br />
== P ==<br />
<br />
<br />
*[http://cst.dk/patrizia/ Paggio, Patrizia] - University of Copenhagen<br />
*[http://www.slt.atr.co.jp/~kpaik/ Paik, Kyonghee] - ATR Spoken Language Translation Research Laboratories<br />
*[http://www.cs.cornell.edu/People/pabo Pang, Bo] - Cornell University<br />
*[http://verbs.colorado.edu/~mpalmer/ Palmer, Martha] - University of Colorado<br />
*[http://www.isi.edu/~pantel/ Pantel, Patrick] - ISI/University of Southern California<br />
*[http://www.cs.columbia.edu/~becky/ Passonneau, Rebecca] Columbia University and Bellcore<br />
*[http://www.ilsp.gr/homepages/pastra_eng.html/ Pastra, Katerina] Institute for Language and Speech Processing<br />
*[http://www.cs.utah.edu/~sidd Patwardhan, Siddharth] - University of Utah<br />
*[http://www.l2f.inesc-id.pt/~joana/english.html Paulo Pardal] - Joana L&sup2;F] - INESC-ID<br />
*[http://perswww.kuleuven.be/yves_peirsman Peirsman, Yves] - University of Leuven<br />
*[http://www.d.umn.edu/~tpederse Pedersen, Ted] - University of Minnesota, Duluth<br />
*[http://ai-nlp.info.uniroma2.it/pennacchiotti Pennacchiotti, Marco] - University of Roma Tor Vergata<br />
*[http://www.perry.com/ Perry, John] - UCLA<br />
*[http://tcc.itc.it/people/pianesi.html Pianesi, Fabio] - ITC-irst <br />
*[http://www.resegone.com/mapb/ Piccolino Boniforti, Marco Aldo] - Rovira i Virgili University<br />
*[http://cswww.essex.ac.uk/staff/poesio Poesio, Massimo] - University of Essex<br />
*[http://www.fas.umontreal.ca/ling/olst/polguereE Polguere, Alain] - Université de Montréal<br />
*[http://fas.sfu.ca/0h/cs/people/Faculty/Popowich/popowich Popowich, Fred] - Simon Fraser University<br />
*[http://nlp.ipipan.waw.pl/~adamp/ Przepiórkowski, Adam] - Polish Academy of Sciences, Warsaw<br />
*[http://www.ling-phil.ox.ac.uk/people/staff/pulman/ Pulman, Stephen] - Oxford University<br />
*[http://www.cs.brandeis.edu/~jamesp Pustejovsky, James] - Brandeis University<br />
<br />
== Q ==<br />
<br />
== R ==<br />
<br />
*[http://www.eecs.umich.edu/~radev/ Radev, Dragomir] - University of Michigan<br />
*[http://www1.cs.columbia.edu/~rambow/ Rambow, Owen] - CCLS, Columbia University<br />
*[http://www.fask.uni-mainz.de/user/rapp Rapp, Reinhard] - Johannes Gutenberg-Universitaet Mainz<br />
*[http://www.cs.buffalo.edu/pub/WWW/faculty/rapaport/rapaport.html Rapaport, William J.] - SUNY Buffalo<br />
*[http://www.cam.sri.com/manny.html Rayner, Manny] SRI International<br />
*[http://www.cis.upenn.edu/~cliff-group/94/lrau.html Rau, Lisa]<br />
*[http://www.comp.lancs.ac.uk/computing/users/paul/ Rayson, Paul] - Lancaster University<br />
*[http://sivareddy.in Reddy, Siva] - University of York, Lexical Computing Ltd, UK<br />
*[http://www.csd.abdn.ac.uk/~ereiter Reiter, Ehud] - University of Aberdeen<br />
*[http://www.dfki.uni-sb.de/~bert Reithinger, Norbert] - Universität des Saarlandes<br />
*[http://www.reitter-it-media.de/ Reitter, David] - University of Edinburgh<br />
*[http://www.ai.mit.edu/~jrennie/ Rennie, Jason] - MIT<br />
*[http://umiacs.umd.edu/~resnik Resnik, Philip] - University of Maryland, College Park<br />
*[http://www.cs.utah.edu/~riloff/ Riloff, Ellen] - University of Utah<br />
*[http://www.cs.rochester.edu/u/ringger/ Ringger, Eric,] - University of Rochester<br />
*[http://www.di.ufpe.br/~jr Robin, Jacques, Federal] - University of Pernambuco, Brazil.<br />
*[http://www.univ-ab.pt/~vjr/ Rocio, Vitor] - Open University, Lisbon<br />
*[http://jones.ling.indiana.edu/~prrodrig/ Rodrigues, Paul] - Indiana University, Bloomington<br />
*[http://www.uteroemer.de/ Romer, Ute] University of Hanover<br />
*[http://www.people.cornell.edu/pages/mr249/ Rooth, Mats] - Cornell University<br />
*[http://l2r.cs.uiuc.edu Roth, Dan] - University of Illinois, Urbana-Champaign<br />
*[http://www.public.asu.edu/~droussi/ Roussinov, Dmitri] - Arizona State University<br />
*[http://www.hi.is/~eirikur/ Rögnvaldsson, Eiríkur] - University of Iceland<br />
*[http://www.uteroemer.de/ Römer, Ute] - University of Hanover<br />
*[http://rykov-cl.narod.ru/ Rykov, Vladimir]<br />
<br />
== S ==<br />
<br />
*[http://ixa.si.ehu.es/Ixa/Argitalpenak/kidearen_argitalpenak?kidea=1000809006 Sarasola, Kepa] - University of the Basque Country<br />
*[http://coli.uni-sb.de/~christer Samuelsson, Christer] Bell Labs<br />
*[http://www.cs.sfu.ca/~anoop/ Sarkar, Anoop] - currently at Simon Fraser University, formerly at University of Pennsylvania<br />
*[http://personalpages.manchester.ac.uk/staff/yutaka.sasaki/ Sasaki, Yutaka] - University of Manchester<br />
*[http://www.cog.jhu.edu/~savova/ Savova, Virginia] - MIT<br />
*[http://www.dei.unipd.it/~satta Satta, Giorgio] University of Padua<br />
*[http://www.dfki.de/~uschaefer Schaefer, Ulrich] - German Research Center for Artificial Intelligence<br />
*[http://www7.informatik.tu-muenchen.de/~scheler Scheler] - Gabriele, TU München<br />
*[http://www.ims.uni-stuttgart.de/~mike/ Schiehlen, Michael] - University of Stuttgart<br />
*[http://www.ims.uni-stuttgart.de/~schmid/ Schmid, Helmut] - University of Stuttgart<br />
*[http://www.kde.cs.uni-kassel.de/schmitz Schmitz, Christoph] - Universität Kassel<br />
*[http://www.schulteimwalde.de/ Schulte, Sabine, im Walde]<br />
*[http://www.ics.mq.edu.au/~rolfs Schwitter, Rolf] - Macquarie University<br />
*[http://mcs.open.ac.uk/ds5473/ Scott, Donia] - The Open University<br />
*[http://nlp.cs.nyu.edu/sekine Sekine, Satoshi] - New York University<br />
*[http://www.latl.unige.ch/personal/vseretan Seretan, Violeta] - University of Geneva<br />
*[http://sites.google.com/site/khaledshaalan/ Shaalan, Khaled] - Cairo University<br />
*[http://www.cs.man.ac.uk/~shamsbaa/ Shams, Armin] - Metro College of Management Sciences, Manchester<br />
*[http://www.eecs.harvard.edu/~shieber/ Shieber, Stuart] - Harvard University<br />
*[http://mysite.verizon.net/sidner Sidner, Candy] - BAE Systems, AIT<br />
*[http://www.cs.rochester.edu/u/sikorski/ Sikorski, Teresa] - University of Rochester<br />
*[http://www.lingsoft.fi/~silvonen/ Silvonen, Mikko] - Lingsoft, Inc.<br />
*[http://www.bultreebank.org/kivs/ Simov, Kiril] - Bulgarian Academy of Sciences<br />
*[http://ltrc.iiit.net/anil Singh, Anil Kumar] - Language Technologies Research Centre (LTRC), International Institute of Information Technology (IIIT), Hyderabad, India<br />
*[http://www.utexas.edu/cola/centers/lrc/general/facultyhomes/jonathan.html Slocum, Jonathan] - The University of Texas at Austin<br />
*[http://www.cs.cmu.edu/~nasmith Smith, Noah] - Carnegie Mellon University<br />
*[http://www.cog.jhu.edu/faculty/smolensky.html Smolensky, Paul] - Johns Hopkins University<br />
*[http://www.ccl.umist.ac.uk/harold/ Somers, Harold] UMIST, Manchester<br />
*[http://www.ece.uiuc.edu/faculty/faculty.asp?rws Sproat, Richard] - University of Illinois, Urbana-Champaign<br />
*[http://www.coling.uni-freiburg.de/~staab/staab.html Staab, Steffen] - Freiburg University<br />
*[http://www.humnet.ucla.edu/humnet/linguistics/people/stabler/stabler.htm Stabler, Edward] - UCLA<br />
*[http://slt.wcl.ee.upatras.gr/stamatatos/personal.html Stamatatos, Efstathios] - University of Patras<br />
*[http://www.cs.toronto.edu/~suzanne/ Stevenson, Suzanne] - University of Toronto<br />
*[http://isl.ira.uka.de/~stiefel Stiefelhagen, Rainer] - Universität Karlsruhe<br />
*[http://www.coling.uni-freiburg.de/~strube/strube.html Strube, Michael] - University of Freiburg<br />
*[http://lvs004.googlepages.com Subramaniam, L. Venkata] - IBM India Research Lab<br />
*[http://www.csi.uottawa.ca/~szpak/ Szpakowicz, Stan] - University of Ottawa<br />
<br />
== T ==<br />
<br />
*[http://www.sfu.ca/~mtaboada Taboada, Maite] - Simon Fraser University<br />
*[http://hnk.ffzg.hr/mt/ Tadic, Marko] - Faculty of Philosophy, University of Zagreb<br />
*[http://www.ling.helsinki.fi/~tapanain Tapanainen, Pasi] - University of Helsinki<br />
*[http://www8.informatik.uni-erlangen.de/inf8/en/thabet.html Thabet, Iman] - University of Erlangen-Nuremberg<br />
*[http://www.siit.tu.ac.th/dirctory/ft_fac/thanaruk.html Theeramunkong, Thanaruk] - Sirindhorn International Institute of Technology, Thammasat University<br />
*[http://www.objs.com/thompson.htm Thompson, Craig] - Object Services and Consulting, Inc.<br />
*[http://www.let.rug.nl/~tiedeman/blog/index.php?category=1 Tiedemann, Jörg] - University of Groningen<br />
*[http://lia.univ-avignon.fr/fileadmin/documents/Users/Intranet/chercheurs/torres/ Torres-Moreno, Juan-Manuel] - LIA, Université d'Avignon (France)<br />
*[http://tecfa.unige.ch/tecfa-people/traum.html Traum, David] - TECFA, Universite de Geneve<br />
*[http://www.hum.uit.no/a/trond/ Trosterud, Trond] - University of Tromsø<br />
*[http://www.racai.ro/~tufis/ Tufis, Dan] - Research Institute for Artificial Intelligence, Romanian Academy<br />
*[http://www.apperceptual.com/ Turney, Peter] - National Research Council of Canada<br />
<br />
== U ==<br />
<br />
*[http://www.coli.uni-sb.de/~hansu Uszkoreit, Hans] - University of the Saarland and DFKI Saarbrücken<br />
<br />
== V ==<br />
<br />
*[http://www.q-go.com/ van de Burgt, Stan P.] - Q-go.com<br />
*[http://www.ccl.kuleuven.be/~vincent/ccl/ Vandeghinste, Vincent] - K.U.Leuven<br />
*[http://ilk.uvt.nl/~antalb/ van den Bosch, Antal] - Tilburg University<br />
*[http://www.media.mit.edu/~nwv/ Van Dyke, Neil] - MIT Media Lab<br />
*[http://www.let.rug.nl/~vannoord/ van Noord, Gertjan] University of Groningen<br />
*[http://www.ua.es/personal/chelo.vargas Vargas, Chelo Sierra] - Universidad de Alicante<br />
*[http://grid.let.rug.nl/~mettina/ Veenstra, Mettina] University of Groningen<br />
*[http://www.cs.brandeis.edu/~marc/home.html Verhagen, Marc] - Brandeis University<br />
*[http://www.up.univ-mrs.fr/veronis/ Véronis, Jean] - Université de Provence<br />
*[http://www.dlsi.ua.es/~vicedo/vicedo_en.html Vicedo, Jose Luis] - Alicante University<br />
*[http://www.inf.unisinos.br/~renata/ Vieira, Renata] - Universidade do Vale do Rio dos Sinos, Brazil<br />
*[http://www.cl.cam.ac.uk/~av208/ Villavicencio, Aline] - Federal University of Rio Grande do Sul, Brazil<br />
*[http://home.planet.nl/~weiss075/ Vossen, Piek] Irion Technologies<br />
*[http://www.ling.helsinki.fi/~avoutila/ Voutilainen, Atro] - University of Helsinki<br />
<br />
== W ==<br />
<br />
*[http://www.dfki.de/~wahlster/ Wahlster, Wolfgang] - Universität des Saarlandes<br />
*[http://www.uindy.gr/faculty/cv/wallace_manolis/ Wallace, Manolis] - National Technical University of Athens<br />
*[http://www.nigelward.com/ Ward, Nigel]<br />
*[http://www.ribbitsoft.com/research/watson/index.html Watson, Bruce] Ribbit Soft.<br />
*[http://hiplab.newcastle.edu.au/~pwatters Watters, Paul A. ] U. of Newcastle, Australia<br />
*[http://www.nick-webb.net Webb, Nick] - SUNY Albany<br />
*[http://www.pages.drexel.edu/~rw37/ Weber, Rosina] - Drexel University<br />
*[http://www.ucsc.cmb.ac.lk/People/rw Weerasinghe, Ruvan] - University of Colombo School of Computing<br />
*[http://www.latl.unige.ch/personal/eric_f.html Wehrli, Eric] - University of Geneva<br />
*[http://www.cs.tu-berlin.de/~ww/ Weisweber, Wilhelm] - Technical University of Berlin<br />
*[http://www.ukp.tu-darmstadt.de Weimer, Markus] - University of Technology Darmstadt<br />
*[http://www.cis.upenn.edu/~bonnie Webber, Bonnie Lynn] - University of Pennsylvania<br />
*[http://www.dcs.shef.ac.uk/~yorick Wilks, Yorick] - University of Sheffield<br />
*[http://cs.haifa.ac.il/~shuly Wintner, Shuly] - University of Haifa, Israel<br />
*[http://www.se.cuhk.edu.hk/~kfwong/ Wong, Kam-Fai] - Chinese University of Hong Kong<br />
*[http://explorer.csse.uwa.edu.au/resume Wong, Wilson] - University of Western Australia<br />
*[http://www.cs.utexas.edu/users/ywwong/ Wong, Yuk Wah] - University of Texas at Austin<br />
*[http://www.cs.man.ac.uk/~wroec/ Wroe, Chris] - University of Manchester<br />
*[http://www.cs.ust.hk/faculty/dekai/bio.html Wu, Dekai] - HKUST<br />
<br />
== X ==<br />
*[http://faculty.washington.edu/fxia/ Xia, Fei] - University of Washington<br />
*[http://www1.i2r.a-star.edu.sg/~dyxiong/ Xiong, Deyi] - Institute for Infocomm Research, Singapore<br />
<br />
== Y ==<br />
<br />
*[http://www.cs.helsinki.fi/u/yangarbe/ Yangarber, Roman] - University of Helsinki<br />
*[http://www.cis.upenn.edu/~cliff-group/94/yarowsky.html Yarowsky, David] - University of Pennsylvania<br />
*[http://www.icl.pku.edu.cn/member/yusw/ Yu, Shiwen] - Peking University<br />
*[http://www.denizyuret.com/ Yuret, Deniz] - Koç University<br />
<br />
== Z ==<br />
<br />
*[http://ufal.mff.cuni.cz/~zabokrtsky Žabokrtský, Zdeněk] - Charles University in Prague<br />
*[http://ai-nlp.info.uniroma2.it/zanzotto Zanzotto, Fabio Massimo] - University of Roma Tor Vergata<br />
*[http://ufal.mff.cuni.cz/~zeman/ Zeman, Dan] - Univerzita Karlova v&nbsp;Praze<br />
*[http://www.ukp.tu-darmstadt.de/ Zesch, Torsten] - Darmstadt University of Technology<br />
*[http://www1.i2r.a-star.edu.sg/~mzhang/ Zhang, Min] - Institute for Infocomm Research, Singapore<br />
*[http://bcmi.sjtu.edu.cn/~zhaohai/ Zhao, Hai] - City University of Hong Kong<br />
*[http://pages.cs.wisc.edu/~jerryzhu/ Zhu, Xiaojin (Jerry)] - University of Wisconsin, Madison<br />
*[http://www.csse.monash.edu.au/~ingrid/ Zukerman, Ingrid] - Monash University</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Kannada&diff=9061Resources for Kannada2011-11-06T13:55:40Z<p>Sivareddy: </p>
<hr />
<div>==Kannada POS tagger==<br />
<br />
[http://sivareddy.in/downloads Download]<br />
<br />
<b>Related Publication:</b><br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Resources_for_Kannada&diff=9060Resources for Kannada2011-11-06T13:54:44Z<p>Sivareddy: Created page with "==Kannada POS tagger== [http://sivareddy.in/downloads Download] Related Publication: Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross L..."</p>
<hr />
<div>==Kannada POS tagger==<br />
<br />
[http://sivareddy.in/downloads Download]<br />
<br />
Related Publication:<br />
<br />
Siva Reddy, Serge Sharoff. [http://sivareddy.in/papers/clia2011IndianCrossLang.pdf Cross Language POS Taggers (and other Tools) for Indian Languages: An Experiment with Kannada using Telugu Resources.] In Proceedings of IJCNLP workshop on Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies. (CLIA 2011 at IJNCLP 2011), Chiang Mai, Thailand [http://sivareddy.in/papers/reddy2011crosslang.bib Bibtex]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=List_of_resources_by_language&diff=9059List of resources by language2011-11-06T13:51:01Z<p>Sivareddy: </p>
<hr />
<div>List of pages which give links and commentary on computational resources by language.<br />
<br />
Quick Links:<br />
<br />
* [[Resources for English]]<br />
* [[Multilingual resources|Resources for Multilingual Applications]]<br />
<br />
<br />
==A==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Albanian]]<br />
* [[Resources for Amharic]]<br />
* [[Resources for Arabic]]<br />
* [[Resources for Afrikaans]]<br />
<br />
==B==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Basque]]<br />
* [[Resources for Bulgarian]]<br />
* [[Resources for Breton]]<br />
<br />
==C==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Catalan]]<br />
* [[Resources for Chinese]]<br />
* [[Resources for Croatian]] (see also [[Resources for Serbian]], [[Resources for Bosnian]], [[Resources for Serbo-Croatian]])<br />
* [[Resources for Czech]]<br />
<br />
==D==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Danish]]<br />
* [[Resources for Dutch]]<br />
<br />
==E==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for English]]<br />
* [[Resources for Estonian]]<br />
<br />
==F==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Faroese]]<br />
* [[Resources for Finnish]]<br />
* [[Resources for French]]<br />
<br />
==G==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Galician]]<br />
* [[Resources for Georgian]]<br />
* [[Resources for German]]<br />
* [[Resources for Greek]]<br />
* [[Resources for Greenlandic]]<br />
<br />
==H==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Haitian]]<br />
* [[Resources for Hebrew]]<br />
* [[Resources for Hindi]]<br />
<br />
==I==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Icelandic]]<br />
* [[Resources for Iñupiaq]]<br />
* [[Resources for Iranian]]<br />
* [[Resources for Italian]]<br />
* [[Resources for Irish]]<br />
<br />
==J==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Japanese]]<br />
<br />
==K==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Kannada]]<br />
* [[Resources for Korean]]<br />
* [[Resources for Komi]]<br />
* [[Resources for Kurdish]]<br />
<br />
==L==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Lithuanian]]<br />
<br />
==M==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Macedonian]]<br />
* [[Resources for Malay]]<br />
* [[Resources for Maltese]]<br />
* [[Resources for Montenegrin]]<br />
* [[Multilingual resources|Resources for Multilingual Applications]]<br />
<br />
==N==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Norwegian]]<br />
* [[Resources for Navajo]]<br />
<br />
==O==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Occitan]]<br />
<br />
==P==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Pashto]]<br />
* [[Resources for Persian]]<br />
* [[Resources for Polish]]<br />
* [[Resources for Portugese]]<br />
* [[Resources for Punjabi]]<br />
<br />
==Q==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Quechua]]<br />
<br />
==R==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Romanian]]<br />
* [[Resources for Russian]]<br />
<br />
==S==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Sámi]]<br />
* [[Resources for Sanskrit]]<br />
* [[Resources for Slovak]]<br />
* [[Resources for Slovenian]]<br />
* [[Resources for Sorbian]]<br />
* [[Resources for Spanish]]<br />
* [[Resources for Swahili]]<br />
* [[Resources for Swedish]]<br />
<br />
==T==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Tajik]]<br />
* [[Resources for Turkish]]<br />
* [[Resources for Tigrinya]]<br />
<br />
==U==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Ukrainian]]<br />
* [[Resources for Urdu]]<br />
<br />
==V==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Vietnamese]]<br />
<br />
==W==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Welsh]]<br />
<br />
==Z==<br />
__NOTOC__<br />
{{compactTOC2}}<br />
* [[Resources for Zulu]]<br />
<br />
==See also==<br />
<br />
* [[Resources for African languages]]<br />
<br />
[[Category:Resources by language|*]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Best_paper_awards&diff=9058Best paper awards2011-11-06T13:42:39Z<p>Sivareddy: </p>
<hr />
<div>=ACL=<br />
<br />
A few items are still missing. Please help complete this table.<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2001<br />
|Eugene Charniak<br />
|Immediate-head parsing for language modeling <br />
|-<br />
|2001<br />
|Ulrich Germann, Michael Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada<br />
|Fast Decoding and Optimal Decoding for Machine Translation<br />
|-<br />
|2002<br />
|Franz Och and Hermann Ney<br />
|Discriminative Traing and Maximum Entropy Models for Statistical Machine Translation<br />
|-<br />
|2003<br />
|Dan Klein and Chris Manning<br />
|Accurate Unlexicalized Parsing<br />
|-<br />
|2003<br />
|Yukiko Nakano, Gabe Reinstein, Tom Stocky, and Justine Cassell<br />
|Towards a Model of Face-to-Face Grounding<br />
|-<br />
|2004<br />
|Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll<br />
|Finding Predominant Word Senses in Untagged Text<br />
|-<br />
|2005<br />
|David Chiang<br />
|A hierarchical phrase-based model for statistical machine translation<br />
|-<br />
|2006<br />
|Rion Snow, Dan Jurafsky, and Andrew Y. Ng<br />
|Semantic taxonomy induction from heterogenous evidence<br />
|-<br />
|2007<br />
|Y. W. Wong and R. J. Mooney<br />
|Learning synchronous grammars for semantic parsing with lambda calculus<br />
|-<br />
|2008<br />
|Liang Huang<br />
|Forest Reranking: Discriminative Parsing with Non-Local Features<br />
|-<br />
|2008<br />
|Libin Shen, Jinxi Xu and Ralph Weischedel<br />
|A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model<br />
|-<br />
|2009<br />
|Andre Martins, Noah Smith and Eric Xing<br />
|Concise Integer Linear Programming Formulations for Dependency Parsing<br />
|-<br />
|2009<br />
|S.R.K. Branavan, Harr Chen, Luke Zettlemoyer and Regina Barzilay<br />
|Reinforcement Learning for Mapping Instructions to Actions<br />
|-<br />
|2009<br />
|Adam Pauls and Dan Klein<br />
|K-Best A* Parsing <br />
|-<br />
|2010 (Long)<br />
|Matthew Gerber and Joyce Chai<br />
|Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates<br />
|-<br />
|2010 (Short)<br />
|Michael Lamar, Yariv Maron, Mark Johnson and Elie Bienenstock<br />
|SVD and Clustering for Unsupervised POS Tagging<br />
|-<br />
|2010 (Student)<br />
|David Elson, Nicholas Dames and Kathleen McKeown<br />
|Extracting Social Networks from Literary Fiction<br />
|-<br />
|2011<br />
|Dipanjan Das and Slav Petrov<br />
|Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections<br />
|-<br />
|}<br />
<br />
=NAACL=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2004<br />
|Regina Barzilay, MIT, and Lillian Lee, Cornell<br />
|Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization<br />
|-<br />
|2006<br />
|Mehryar Mohri and Brian Roark<br />
|Probabilistic Context-Free Grammar Induction Based on Structural Zeros<br />
|-<br />
|2006<br />
|Aria Haghighi and Dan Klein<br />
|Prototype-Driven Learning for Sequence Models<br />
|-<br />
|2007<br />
|Antti-Veikko Rosti, Bing Xiang, Spyros Matsoukas, Richard Schwartz, Necip Fazil Ayan and Bonnie Dorr<br />
|Combining Outputs from Multiple Machine Translation Systems<br />
|-<br />
|2009<br />
|Hoifung Poon, Colin Cherry and Kristina Toutanova<br />
|Unsupervised Morphological Segmentation with Log-Linear Models<br />
|-<br />
|2009<br />
|David Chiang, Kevin Knight and Wei Wang<br />
|11,001 New Features for Statistical Machine Translationz<br />
|}<br />
<br />
=EMNLP=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2002<br />
|Michael Collins<br />
|Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms<br />
|-<br />
|2002<br />
|Frank Keller, Maria Lapata, and Olga Ourioupina<br />
|Using the Web to Overcome Data Sparseness<br />
|-<br />
|2003<br />
|Peng Xu, Ahmad Emami and Frederick Jelinek<br />
|Training Connectionist Models for the Structured Language Model<br />
|-<br />
|2004<br />
|Ben Taskar, Dan Klein, Michael Collins, Daphne Koller, and Christopher Manning<br />
|Max-Margin Parsing<br />
|-<br />
|2005 (best student paper)<br />
|Ryan McDonald, Fernando Pereira, Kiril Ribarov and Jan Hajic<br />
|Non-Projective Dependency Parsing using Spanning Tree Algorithms<br />
|-<br />
|2006<br />
|no award given<br />
|<br />
|-<br />
|2007<br />
|James Clarke and Maria Lapata<br />
|Modelling Compression with Discourse Constraints<br />
|-<br />
|2008<br />
|no award given<br />
|<br />
|-<br />
|2009<br />
|Hoifung Poon and Pedro Domingos<br />
|Unsupervised semantic parsing<br />
|}<br />
<br />
<br />
=IJCNLP=<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2009<br />
|Andre Martins, Noah Smith and Eric Xing<br />
|Concise Integer Linear Programming Formulations for Dependency Parsing<br />
|-<br />
|2009<br />
|S.R.K. Branavan, Harr Chen, Luke Zettlemoyer and Regina Barzilay<br />
|Reinforcement Learning for Mapping Instructions to Actions<br />
|-<br />
|2009<br />
|Adam Pauls and Dan Klein<br />
|K-Best A* Parsing <br />
|-<br />
|}<br />
[[Category:Awards]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Best_paper_awards&diff=9057Best paper awards2011-11-06T13:37:22Z<p>Sivareddy: </p>
<hr />
<div>=ACL=<br />
<br />
A few items are still missing. Please help complete this table.<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2001<br />
|Eugene Charniak<br />
|Immediate-head parsing for language modeling <br />
|-<br />
|2001<br />
|Ulrich Germann, Michael Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada<br />
|Fast Decoding and Optimal Decoding for Machine Translation<br />
|-<br />
|2002<br />
|Franz Och and Hermann Ney<br />
|Discriminative Traing and Maximum Entropy Models for Statistical Machine Translation<br />
|-<br />
|2003<br />
|Dan Klein and Chris Manning<br />
|Accurate Unlexicalized Parsing<br />
|-<br />
|2003<br />
|Yukiko Nakano, Gabe Reinstein, Tom Stocky, and Justine Cassell<br />
|Towards a Model of Face-to-Face Grounding<br />
|-<br />
|2004<br />
|Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll<br />
|Finding Predominant Word Senses in Untagged Text<br />
|-<br />
|2005<br />
|David Chiang<br />
|A hierarchical phrase-based model for statistical machine translation<br />
|-<br />
|2006<br />
|Rion Snow, Dan Jurafsky, and Andrew Y. Ng<br />
|Semantic taxonomy induction from heterogenous evidence<br />
|-<br />
|2007<br />
|Y. W. Wong and R. J. Mooney<br />
|Learning synchronous grammars for semantic parsing with lambda calculus<br />
|-<br />
|2008<br />
|Liang Huang<br />
|Forest Reranking: Discriminative Parsing with Non-Local Features<br />
|-<br />
|2008<br />
|Libin Shen, Jinxi Xu and Ralph Weischedel<br />
|A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model<br />
|-<br />
|2009<br />
|Andre Martins, Noah Smith and Eric Xing<br />
|Concise Integer Linear Programming Formulations for Dependency Parsing<br />
|-<br />
|2009<br />
|S.R.K. Branavan, Harr Chen, Luke Zettlemoyer and Regina Barzilay<br />
|Reinforcement Learning for Mapping Instructions to Actions<br />
|-<br />
|2009<br />
|Adam Pauls and Dan Klein<br />
|K-Best A* Parsing <br />
|-<br />
|2010 (Long)<br />
|Matthew Gerber and Joyce Chai<br />
|Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates<br />
|-<br />
|2010 (Short)<br />
|Michael Lamar, Yariv Maron, Mark Johnson and Elie Bienenstock<br />
|SVD and Clustering for Unsupervised POS Tagging<br />
|-<br />
|2010 (Student)<br />
|David Elson, Nicholas Dames and Kathleen McKeown<br />
|Extracting Social Networks from Literary Fiction<br />
|-<br />
|2011<br />
|Dipanjan Das and Slav Petrov<br />
|Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections<br />
|-<br />
|}<br />
<br />
=NAACL=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2004<br />
|Regina Barzilay, MIT, and Lillian Lee, Cornell<br />
|Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization<br />
|-<br />
|2006<br />
|Mehryar Mohri and Brian Roark<br />
|Probabilistic Context-Free Grammar Induction Based on Structural Zeros<br />
|-<br />
|2006<br />
|Aria Haghighi and Dan Klein<br />
|Prototype-Driven Learning for Sequence Models<br />
|-<br />
|2007<br />
|Antti-Veikko Rosti, Bing Xiang, Spyros Matsoukas, Richard Schwartz, Necip Fazil Ayan and Bonnie Dorr<br />
|Combining Outputs from Multiple Machine Translation Systems<br />
|-<br />
|2009<br />
|Hoifung Poon, Colin Cherry and Kristina Toutanova<br />
|Unsupervised Morphological Segmentation with Log-Linear Models<br />
|-<br />
|2009<br />
|David Chiang, Kevin Knight and Wei Wang<br />
|11,001 New Features for Statistical Machine Translationz<br />
|}<br />
<br />
=EMNLP=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2002<br />
|Michael Collins<br />
|Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms<br />
|-<br />
|2002<br />
|Frank Keller, Maria Lapata, and Olga Ourioupina<br />
|Using the Web to Overcome Data Sparseness<br />
|-<br />
|2003<br />
|Peng Xu, Ahmad Emami and Frederick Jelinek<br />
|Training Connectionist Models for the Structured Language Model<br />
|-<br />
|2004<br />
|Ben Taskar, Dan Klein, Michael Collins, Daphne Koller, and Christopher Manning<br />
|Max-Margin Parsing<br />
|-<br />
|2005 (best student paper)<br />
|Ryan McDonald, Fernando Pereira, Kiril Ribarov and Jan Hajic<br />
|Non-Projective Dependency Parsing using Spanning Tree Algorithms<br />
|-<br />
|2006<br />
|no award given<br />
|<br />
|-<br />
|2007<br />
|James Clarke and Maria Lapata<br />
|Modelling Compression with Discourse Constraints<br />
|-<br />
|2008<br />
|no award given<br />
|<br />
|-<br />
|2009<br />
|Hoifung Poon and Pedro Domingos<br />
|Unsupervised semantic parsing<br />
|}<br />
<br />
<br />
[[Category:Awards]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Best_paper_awards&diff=9056Best paper awards2011-11-06T13:30:40Z<p>Sivareddy: </p>
<hr />
<div>=ACL=<br />
<br />
A few items are still missing. Please help complete this table.<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2001<br />
|Eugene Charniak<br />
|Immediate-head parsing for language modeling <br />
|-<br />
|2001<br />
|Ulrich Germann, Michael Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada<br />
|Fast Decoding and Optimal Decoding for Machine Translation<br />
|-<br />
|2002<br />
|Franz Och and Hermann Ney<br />
|Discriminative Traing and Maximum Entropy Models for Statistical Machine Translation<br />
|-<br />
|2003<br />
|Dan Klein and Chris Manning<br />
|Accurate Unlexicalized Parsing<br />
|-<br />
|2003<br />
|Yukiko Nakano, Gabe Reinstein, Tom Stocky, and Justine Cassell<br />
|Towards a Model of Face-to-Face Grounding<br />
|-<br />
|2004<br />
|Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll<br />
|Finding Predominant Word Senses in Untagged Text<br />
|-<br />
|2005<br />
|David Chiang<br />
|A hierarchical phrase-based model for statistical machine translation<br />
|-<br />
|2006<br />
|Rion Snow, Dan Jurafsky, and Andrew Y. Ng<br />
|Semantic taxonomy induction from heterogenous evidence<br />
|-<br />
|2007<br />
|Y. W. Wong and R. J. Mooney<br />
|Learning synchronous grammars for semantic parsing with lambda calculus<br />
|-<br />
|2008<br />
|Liang Huang<br />
|Forest Reranking: Discriminative Parsing with Non-Local Features<br />
|-<br />
|2008<br />
|Libin Shen, Jinxi Xu and Ralph Weischedel<br />
|A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model<br />
|-<br />
|2009<br />
|Andre Martins, Noah Smith and Eric Xing<br />
|Concise Integer Linear Programming Formulations for Dependency Parsing<br />
|-<br />
|2009<br />
|S.R.K. Branavan, Harr Chen, Luke Zettlemoyer and Regina Barzilay<br />
|Reinforcement Learning for Mapping Instructions to Actions<br />
|-<br />
|2009<br />
|Adam Pauls and Dan Klein<br />
|K-Best A* Parsing <br />
|-<br />
|2010 (Long)<br />
|Matthew Gerber and Joyce Chai<br />
|Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates<br />
|-<br />
|2010 (Short)<br />
|Michael Lamar, Yariv Maron, Mark Johnson and Elie Bienenstock<br />
|SVD and Clustering for Unsupervised POS Tagging<br />
|-<br />
|2010 (Student)<br />
|David Elson, Nicholas Dames and Kathleen McKeown<br />
|Extracting Social Networks from Literary Fiction<br />
|-<br />
|}<br />
<br />
=NAACL=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2004<br />
|Regina Barzilay, MIT, and Lillian Lee, Cornell<br />
|Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization<br />
|-<br />
|2006<br />
|Mehryar Mohri and Brian Roark<br />
|Probabilistic Context-Free Grammar Induction Based on Structural Zeros<br />
|-<br />
|2006<br />
|Aria Haghighi and Dan Klein<br />
|Prototype-Driven Learning for Sequence Models<br />
|-<br />
|2007<br />
|Antti-Veikko Rosti, Bing Xiang, Spyros Matsoukas, Richard Schwartz, Necip Fazil Ayan and Bonnie Dorr<br />
|Combining Outputs from Multiple Machine Translation Systems<br />
|-<br />
|2009<br />
|Hoifung Poon, Colin Cherry and Kristina Toutanova<br />
|Unsupervised Morphological Segmentation with Log-Linear Models<br />
|-<br />
|2009<br />
|David Chiang, Kevin Knight and Wei Wang<br />
|11,001 New Features for Statistical Machine Translationz<br />
|}<br />
<br />
=EMNLP=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2002<br />
|Michael Collins<br />
|Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms<br />
|-<br />
|2002<br />
|Frank Keller, Maria Lapata, and Olga Ourioupina<br />
|Using the Web to Overcome Data Sparseness<br />
|-<br />
|2003<br />
|Peng Xu, Ahmad Emami and Frederick Jelinek<br />
|Training Connectionist Models for the Structured Language Model<br />
|-<br />
|2004<br />
|Ben Taskar, Dan Klein, Michael Collins, Daphne Koller, and Christopher Manning<br />
|Max-Margin Parsing<br />
|-<br />
|2005 (best student paper)<br />
|Ryan McDonald, Fernando Pereira, Kiril Ribarov and Jan Hajic<br />
|Non-Projective Dependency Parsing using Spanning Tree Algorithms<br />
|-<br />
|2006<br />
|no award given<br />
|<br />
|-<br />
|2007<br />
|James Clarke and Maria Lapata<br />
|Modelling Compression with Discourse Constraints<br />
|-<br />
|2008<br />
|no award given<br />
|<br />
|-<br />
|2009<br />
|Hoifung Poon and Pedro Domingos<br />
|Unsupervised semantic parsing<br />
|}<br />
<br />
<br />
[[Category:Awards]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Best_paper_awards&diff=9055Best paper awards2011-11-06T13:29:15Z<p>Sivareddy: </p>
<hr />
<div>=ACL=<br />
<br />
A few items are still missing. Please help complete this table.<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2001<br />
|Eugene Charniak<br />
|Immediate-head parsing for language modeling <br />
|-<br />
|2001<br />
|Ulrich Germann, Michael Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada<br />
|Fast Decoding and Optimal Decoding for Machine Translation<br />
|-<br />
|2002<br />
|Franz Och and Hermann Ney<br />
|Discriminative Traing and Maximum Entropy Models for Statistical Machine Translation<br />
|-<br />
|2003<br />
|Dan Klein and Chris Manning<br />
|Accurate Unlexicalized Parsing<br />
|-<br />
|2003<br />
|Yukiko Nakano, Gabe Reinstein, Tom Stocky, and Justine Cassell<br />
|Towards a Model of Face-to-Face Grounding<br />
|-<br />
|2004<br />
|Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll<br />
|Finding Predominant Word Senses in Untagged Text<br />
|-<br />
|2005<br />
|David Chiang<br />
|A hierarchical phrase-based model for statistical machine translation<br />
|-<br />
|2006<br />
|Rion Snow, Dan Jurafsky, and Andrew Y. Ng<br />
|Semantic taxonomy induction from heterogenous evidence<br />
|-<br />
|2007<br />
|Y. W. Wong and R. J. Mooney<br />
|Learning synchronous grammars for semantic parsing with lambda calculus<br />
|-<br />
|2008<br />
|Liang Huang<br />
|Forest Reranking: Discriminative Parsing with Non-Local Features<br />
|-<br />
|2008<br />
|Libin Shen, Jinxi Xu and Ralph Weischedel<br />
|A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model<br />
|-<br />
|2009<br />
|Andre Martins, Noah Smith and Eric Xing<br />
|Concise Integer Linear Programming Formulations for Dependency Parsing<br />
|-<br />
|2009<br />
|S.R.K. Branavan, Harr Chen, Luke Zettlemoyer and Regina Barzilay<br />
|Reinforcement Learning for Mapping Instructions to Actions<br />
|-<br />
|2009<br />
|Adam Pauls and Dan Klein<br />
|K-Best A* Parsing <br />
|-<br />
|2010 (Long)<br />
|Matthew Gerber and Joyce Chai<br />
|Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates<br />
|-<br />
|2010 (Short)<br />
|Michael Lamar, Yariv Maron, Mark Johnson, Elie Bienenstock<br />
|SVD and Clustering for Unsupervised POS Tagging<br />
|-<br />
|2010 (Student)<br />
|David Elson, Nicholas Dames, Kathleen McKeown<br />
|Extracting Social Networks from Literary Fiction<br />
|-<br />
|}<br />
<br />
=NAACL=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2004<br />
|Regina Barzilay, MIT, and Lillian Lee, Cornell<br />
|Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization<br />
|-<br />
|2006<br />
|Mehryar Mohri and Brian Roark<br />
|Probabilistic Context-Free Grammar Induction Based on Structural Zeros<br />
|-<br />
|2006<br />
|Aria Haghighi and Dan Klein<br />
|Prototype-Driven Learning for Sequence Models<br />
|-<br />
|2007<br />
|Antti-Veikko Rosti, Bing Xiang, Spyros Matsoukas, Richard Schwartz, Necip Fazil Ayan and Bonnie Dorr<br />
|Combining Outputs from Multiple Machine Translation Systems<br />
|-<br />
|2009<br />
|Hoifung Poon, Colin Cherry and Kristina Toutanova<br />
|Unsupervised Morphological Segmentation with Log-Linear Models<br />
|-<br />
|2009<br />
|David Chiang, Kevin Knight and Wei Wang<br />
|11,001 New Features for Statistical Machine Translationz<br />
|}<br />
<br />
=EMNLP=<br />
<br />
{| border="1" cellspacing="0" cellpadding="5"<br />
|'''Year'''<br />
|'''Author'''<br />
|'''Paper Title'''<br />
|-<br />
|2002<br />
|Michael Collins<br />
|Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms<br />
|-<br />
|2002<br />
|Frank Keller, Maria Lapata, and Olga Ourioupina<br />
|Using the Web to Overcome Data Sparseness<br />
|-<br />
|2003<br />
|Peng Xu, Ahmad Emami and Frederick Jelinek<br />
|Training Connectionist Models for the Structured Language Model<br />
|-<br />
|2004<br />
|Ben Taskar, Dan Klein, Michael Collins, Daphne Koller, and Christopher Manning<br />
|Max-Margin Parsing<br />
|-<br />
|2005 (best student paper)<br />
|Ryan McDonald, Fernando Pereira, Kiril Ribarov and Jan Hajic<br />
|Non-Projective Dependency Parsing using Spanning Tree Algorithms<br />
|-<br />
|2006<br />
|no award given<br />
|<br />
|-<br />
|2007<br />
|James Clarke and Maria Lapata<br />
|Modelling Compression with Discourse Constraints<br />
|-<br />
|2008<br />
|no award given<br />
|<br />
|-<br />
|2009<br />
|Hoifung Poon and Pedro Domingos<br />
|Unsupervised semantic parsing<br />
|}<br />
<br />
<br />
[[Category:Awards]]</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=User:Sivareddy&diff=9054User:Sivareddy2011-11-06T13:20:41Z<p>Sivareddy: </p>
<hr />
<div>Name: Siva Reddy<br />
<br />
Webpage: http://sivareddy.in<br />
<br />
CV: http://sivareddy.in/cv_siva.pdf<br />
<br />
Research Interests: Lexical Semantics, Semantic Composition, Multiwords, Machine Learning, Word Sense Disambiguation/Induction, Lexical Acquisition, Web Corpora, Web as a Resource for NLP problems, Cross Language Resources, Syntactic Parsing, Question Answering Inference<br />
<br />
Keywords: Polysemy, Compositionality, Semantic Composition, Domain WSD, Vector Space Models, Semantics, IIIT Hyderabad, York, Lexical Computing Ltd., Sketch Engine</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=User:Sivareddy&diff=9053User:Sivareddy2011-11-06T13:18:14Z<p>Sivareddy: Created page with "Webpage: http://sivareddy.in CV: http://sivareddy.in/cv_siva.pdf Research Interests: Lexical Semantics, Semantic Composition, Multiwords, Machine Learning, Word Sense Disambigu..."</p>
<hr />
<div>Webpage: http://sivareddy.in<br />
<br />
CV: http://sivareddy.in/cv_siva.pdf<br />
<br />
Research Interests: Lexical Semantics, Semantic Composition, Multiwords, Machine Learning, Word Sense Disambiguation/Induction, Lexical Acquisition, Web Corpora, Web as a Resource for NLP problems, Cross Language Resources, Syntactic Parsing, Question Answering Inference</div>Sivareddyhttps://www.aclweb.org/aclwiki/index.php?title=Conference_acceptance_rates&diff=9052Conference acceptance rates2011-11-06T13:13:03Z<p>Sivareddy: </p>
<hr />
<div>==[[ACL]]==<br />
<br />
=== Main Session ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>1997</td><br />
<td>264</td><br />
<td>83</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>1998 (w/COLING)</td><br />
<td>550</td><br />
<td>137</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>1999</td><br />
<td>320</td><br />
<td>80</td><br />
<td>25%</td><br />
</tr><tr> <br />
<td>2000</td><br />
<td>267</td><br />
<td>70</td><br />
<td>26.2%</td><br />
</tr><br />
<tr><br />
<td>2001</td><br />
<td>260</td><br />
<td>69</td><br />
<td>27%</td><br />
</tr><br />
<tr><br />
<td>2002</td><br />
<td>256</td><br />
<td>66</td><br />
<td>26%</td><br />
</tr><br />
<tr><br />
<td>2003</td><br />
<td>360</td><br />
<td>71</td><br />
<td>20%</td><br />
</tr><br />
<tr><br />
<td>2004</td><br />
<td>348</td><br />
<td>88</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2005</td><br />
<td>423</td><br />
<td>77</td><br />
<td>18%</td><br />
</tr><br />
<tr><br />
<td>2006 (w/COLING)</td><br />
<td>630</td><br />
<td>147</td><br />
<td>23%</td><br />
</tr><br />
<tr><br />
<td>2007</td><br />
<td>588</td><br />
<td>131</td><br />
<td>22.3%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>470</td><br />
<td>119</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>569</td><br />
<td>121</td><br />
<td>21%</td><br />
</tr><br />
<tr><br />
<td>2010</td><br />
<td>638</td><br />
<td>160</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2011</td><br />
<td>634</td><br />
<td>164</td><br />
<td>26%</td><br />
</tr><br />
</table><br />
<br />
=== Student Session ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>1992</td><br />
<td>48</td><br />
<td>20</td><br />
<td>42%</td><br />
</tr><br />
<tr><br />
<td>1993</td><br />
<td>30</td><br />
<td>11</td><br />
<td>37%</td><br />
</tr><br />
<tr><br />
<td>1994</td><br />
<td>41</td><br />
<td>10</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>1995</td><br />
<td>48</td><br />
<td>19</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>1996</td><br />
<td>32</td><br />
<td>14</td><br />
<td>44%</td><br />
</tr><br />
<tr><br />
<td>1997</td><br />
<td>42</td><br />
<td>10</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>1998</td><br />
<td>46</td><br />
<td>12</td><br />
<td>26%</td><br />
</tr><br />
<tr><br />
<td>1999</td><br />
<td>30</td><br />
<td>10</td><br />
<td>33%</td><br />
</tr><br />
<tr> <br />
<td>2000</td><br />
<td>36</td><br />
<td>10</td><br />
<td>28%</td><br />
</tr><br />
<tr><br />
<td>2005</td><br />
<td>70</td><br />
<td>26</td><br />
<td>37%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>40</td><br />
<td>15</td><br />
<td>38%</td><br />
</tr><br />
<tr><br />
<td>2007</td><br />
<td>52</td><br />
<td>16</td><br />
<td>31%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>27</td><br />
<td>12</td><br />
<td>44%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>25</td><br />
<td>12</td><br />
<td>48%</td><br />
</tr><br />
</table><br />
<br />
=== Posters/Short Papers ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2005</td><br />
<td>56</td><br />
<td>31</td><br />
<td>55%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>630</td><br />
<td>125</td><br />
<td>20%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>356</td><br />
<td>93</td><br />
<td>26%</td><br />
</tr><br />
</table><br />
<br />
==[[CICLing]]==<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr> <br />
<td>2000</td><br />
<td>??</td><br />
<td>29</td><br />
<td>??</td><br />
</tr><br />
<tr><br />
<td>2001</td><br />
<td>72</td><br />
<td>41</td><br />
<td>57%</td><br />
</tr><br />
<tr> <br />
<td>2002</td><br />
<td>67</td><br />
<td>35</td><br />
<td>52%</td><br />
</tr><br />
<tr> <br />
<td>2003</td><br />
<td>92</td><br />
<td>43</td><br />
<td>46%</td><br />
</tr><br />
<tr> <br />
<td>2004</td><br />
<td>129</td><br />
<td>40</td><br />
<td>31%</td><br />
</tr><br />
<tr> <br />
<td>2005</td><br />
<td>151</td><br />
<td>53</td><br />
<td>35%</td><br />
</tr><br />
<tr> <br />
<td>2006</td><br />
<td>176 (141 full + 35 short)</td><br />
<td>59 (43 full + 16 short)</td><br />
<td>30.4% full & 45.7% short</td><br />
</tr><br />
<tr> <br />
<td>2007</td><br />
<td>179</td><br />
<td>53</td><br />
<td>29.6%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>204</td><br />
<td>52</td><br />
<td>25.5%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>167</td><br />
<td>44</td><br />
<td>26.3%</td><br />
</tr><br />
<tr> <br />
<td>2010</td><br />
<td>271</td><br />
<td>61</td><br />
<td>22.5%</td><br />
</tr><br />
</table><br />
<br />
==[[COLING]]==<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>1998</td><br />
<td>550</td><br />
<td>137</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2000</td><br />
<td>323</td><br />
<td>110</td><br />
<td>34%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>630</td><br />
<td>147</td><br />
<td>23%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>600</td><br />
<td>145</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>2010</td><br />
<td>815</td><br />
<td>334</td><br />
<td>41%</td><br />
</tr><br />
</table><br />
<br />
==[[CONLL]]==<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2003</td><br />
<td>35</td><br />
<td>17</td><br />
<td>48.6%</td><br />
</tr><br />
<tr><br />
<td>2004</td><br />
<td>23</td><br />
<td>11</td><br />
<td>47.8%</td><br />
</tr><br />
<tr><br />
<td>2005</td><br />
<td>70</td><br />
<td>19</td><br />
<td>27%</td><br />
</tr><br />
</table><br />
<br />
==[[EACL]]==<br />
<br />
=== Main Session ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2003</td><br />
<td>?</td><br />
<td>?</td><br />
<td>26.5%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>264</td><br />
<td>52</td><br />
<td>20%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>360</td><br />
<td>100</td><br />
<td>28%</td><br />
</tr><br />
</table><br />
<br />
=== Student Session ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>1993</td><br />
<td>34</td><br />
<td>6</td><br />
<td>18%</td><br />
</tr><br />
<tr><br />
<td>1995</td><br />
<td>37</td><br />
<td>8</td><br />
<td>22%</td><br />
</tr><br />
<tr><br />
<td>1997</td><br />
<td>42</td><br />
<td>10</td><br />
<td>24%</td><br />
</tr><tr><br />
<td>1999</td><br />
<td>17</td><br />
<td>8</td><br />
<td>47%</td><br />
</tr><br />
<tr> <br />
<td>2003</td><br />
<td>18</td><br />
<td>6</td><br />
<td>33.3%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>33</td><br />
<td>9</td><br />
<td>27%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>38</td><br />
<td>11</td><br />
<td>29%</td><br />
</tr><br />
</table><br />
<br />
==[[EMNLP]]==<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>1997</td><br />
<td>??</td><br />
<td>??</td><br />
<td>35%</td><br />
</tr><br />
<tr><br />
<td>2002</td><br />
<td>142</td><br />
<td>35</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2003</td><br />
<td>???</td><br />
<td>28</td><br />
<td>??%</td><br />
</tr><br />
<tr><br />
<td>2004</td><br />
<td>247</td><br />
<td>58</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>2005</td><br />
<td>402</td><br />
<td>127</td><br />
<td>32%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>234</td><br />
<td>73</td><br />
<td>31%</td><br />
</tr><br />
<tr><br />
<td>2007</td><br />
<td>398</td><br />
<td>109</td><br />
<td>27%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>385</td><br />
<td>116</td><br />
<td>30%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>475</td><br />
<td>163</td><br />
<td>34%</td><br />
</tr><br />
<tr><br />
<td>2010</td><br />
<td>500</td><br />
<td>125</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2011</td><br />
<td>628</td><br />
<td>149</td><br />
<td>24%</td><br />
</tr><br />
</table><br />
<br />
==[[NAACL HLT]]==<br />
<br />
=== Main Session ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr> <br />
<td>2000</td><br />
<td>166</td><br />
<td>43</td><br />
<td>26%</td><br />
</tr><br />
<tr><br />
<td>2001</td><br />
<td>110</td><br />
<td>31</td><br />
<td>28%</td><br />
</tr><br />
<tr><br />
<td>2002</td><br />
<td>141</td><br />
<td>28</td><br />
<td>20%</td><br />
</tr><br />
<tr><br />
<td>2003</td><br />
<td>162</td><br />
<td>37</td><br />
<td>23%</td><br />
</tr><br />
<tr><br />
<td>2004</td><br />
<td>168</td><br />
<td>43</td><br />
<td>26%</td><br />
</tr><br />
<tr><br />
<td>2005</td><br />
<td>402</td><br />
<td>127</td><br />
<td>32%</td><br />
</tr><br />
<tr><br />
<td>2006</td><br />
<td>257</td><br />
<td>62</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>2007</td><br />
<td>298</td><br />
<td>72</td><br />
<td>24%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>470</td><br />
<td>119</td><br />
<td>25%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>260</td><br />
<td>75</td><br />
<td>29%</td><br />
</tr><br />
</table><br />
<br />
=== Student Session ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>29</td><br />
<td>17</td><br />
<td>59%</td><br />
</tr><br />
</table><br />
<br />
<br />
==[[IJCNLP]]==<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2004</td><br />
<td>211</td><br />
<td>66</td><br />
<td>31%</td><br />
</tr><br />
<tr> <br />
<td>2005</td><br />
<td>289</td><br />
<td>90</td><br />
<td>31%</td><br />
</tr><br />
<tr><br />
<td>2008</td><br />
<td>270</td><br />
<td>75</td><br />
<td>28%</td><br />
</tr><br />
<tr><br />
<td>2009</td><br />
<td>569</td><br />
<td>121</td><br />
<td>21%</td><br />
</tr><br />
<tr><br />
<td>2011</td><br />
<td>478</td><br />
<td>176</td><br />
<td>36%</td><br />
</tr><br />
</table><br />
<br />
<br />
==[[IWCS]]==<br />
<br />
=== Long Papers ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2011</td><br />
<td>72</td><br />
<td>30</td><br />
<td>42%</td><br />
</tr><br />
</table><br />
<br />
=== Short Papers ===<br />
<br />
<table cellspacing="1" cellpadding="1" border="1" width="20%"><br />
<tr><br />
<th>Year</th><br />
<th>Submitted</th><br />
<th>Accepted</th><br />
<th>Rate</th><br />
</tr><br />
<tr><br />
<td>2011</td><br />
<td>38</td><br />
<td>20</td><br />
<td>53%</td><br />
</tr><br />
</table><br />
<br />
[[Category:Conferences]]</div>Sivareddy