ACL Wiki - User contributions [en]

Resources for Vietnamese

2015-12-17T03:23:22Z

Linas: Link Grammar has prptotype Vietnamese parser

==Dictionaries==
===Free===
===Proprietary===
* [http://gandalf.uib.no/nor-viet-ordbok/ Norwegian-Vietnamese dictionary] from the University of Bergen, TEI XML encoded, 10689 main entries (+6281 sub-entries)

==Tools==
* [http://abisource.com/projects/link-grammar/ Link Grammar Parser], includes prototype Vietnamese dictionaries.

[[Category:Resources by language|Vietnamese]]

Resources for Indonesian

2015-12-17T03:21:11Z

Linas: /* Tools */ Link grammar parser has bare-bones prototype

==Corpora==
* [http://ilps.science.uva.nl/resources/bahasa Kompas and Tempo Online Collection] for evaluation purposes.
* [http://www.panl10n.net/english/OutputsIndonesia2.htm 500,000 Word Bahasa Indonesia Corpus and Parallel English Translation] (A-NC-SA 3.0 licence)
* [http://www.panl10n.net/english/OutputsIndonesia2.htm 500,000 Word Bahasa Indonesia Parallel Corpus with Penn Treebank] (A-NC-SA 3.0 licence)
* [http://www.panl10n.net/english/OutputsIndonesia2.htm One Million POS Tagged Corpus of Bahasa Indonesia] (A-NC-SA 3.0 licence)

==Tools==
* [http://www.panl10n.net/english/OutputsIndonesia2.htm Part of Speech Tagger for Bahasa Indonesia] (GPL licence)
* [https://apertium.svn.sourceforge.net/svnroot/apertium/incubator/apertium-id-ms Rule-based Indonesian-Malay Machine Translation] by [http://dl.dropbox.com/u/537350/paper/MALINDO-2010-final.pdf Septina Dian Larasati]. Possible to use for morphological tagging.
* [http://abisource.com/projects/link-grammar/ Link Grammar Parser], includes prototype Indonesian dictionaries.

[[Category:Resources by language|Indonesian]]

Resources for German

2015-12-17T03:19:40Z

Linas: /* Grammars */ Link parser for German

==Corpora==
===Free license===
* [http://www.computing.dcu.ie/~ygraham/software.html RIA Open Source Rule Induction Tool] includes an LFG-parsed German-English phrase-aligned parallel corpus, a subset of the EuroParl corpus (4000 sentences for each language, the tool at least is LGPL)
* [http://www.euromatrixplus.net/multi-un/ UN parallel corpora]
* [http://www.statmt.org/wmt15/translation-task.html#download WMT corpora], including [http://en.wikipedia.org/wiki/Europarl_corpus Europarl], News Commentary, and News Crawl

===Unknown license===


* [http://ucts.uniba.sk/aranea_about/ Araneum Germanicum], Gigaword German web corpus
* [http://www.phonetik.uni-muenchen.de/Bas/BasKorporaeng.html Bavarian Archive for Speech Signals Corpora]
* [http://corpora.ids-mannheim.de/~cosmas/ COSMAS II]
* [http://www.ims.uni-stuttgart.de/projekte/tc/CQP.html Experimental Corpus Query System (University of Stuttgart, Germany)]
* [http://www.wortschatz.uni-leipzig.de/ German plain text and Co-occurrences at LCC]
* [http://ufal.mff.cuni.cz/hamledt HamleDT], harmonized dependency treebanks of many languages, common annotation style.
* [http://www.coli.uni-sb.de/sfb378/negra-corpus/negra-corpus.html NEGRA Corpus]
* [http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERCorpus/ TIGER treebank]
* [http://www.sfs.uni-tuebingen.de/en_tuebadz.shtml Tübingen Treebank of Written German (TüBa-D/Z)]
* [http://www.sfs.uni-tuebingen.de/en_tuebads.shtml Tübingen Treebank of Spoken German (TüBa-D/S, aka Verbmobil treebank)]
* [http://www.sfs.uni-tuebingen.de/en_tuepp.shtml Tübingen Partially Parsed Corpus of Written German (TüPP-D/Z)]
* [http://www.coli.uni-saarland.de/~gparis/LMD-TAZ_corpus/ Le Monde Diplomatique-Die Tageszeitung Translation Corpus] - French-German, aligned (parallel)

==Evaluation datasets==
* [http://www.ukp.tu-darmstadt.de/data/semRelDatasets Semantic relatedness evaluation]

== Grammars ==
* [[Generation grammars|KPML generation grammar]]
* [http://abisource.com/projects/link-grammar/ Link Grammar Parser], includes prototype German dictionaries.

== Morphological analysis ==
=== Free software ===
* [https://code.google.com/p/morphisto/ Morphisto], based on [[SMOR]], is an [[SFST]]-based analyser and generator for German. (The morphology is GPLv2, but the lexicon is proprietary/non-commercial: CC-BY-SA-NC v3)
* [http://www.danielnaber.de/morphologie/index_en.html German morphology data], based on [http://www.wolfganglezius.de/doku.php?id=cl:morphy Morhpy], licensed under CC-BY-SA 3.0

==Lexicons==
===Free software===
* [http://www-user.tu-chemnitz.de/~fri/ding/ DING] - German-English Dictionary with approximately 253,000 entries (GPL 2 or later).
* [http://www.openthesaurus.de/ OpenThesaurus] - German synonyms and associated terms (LGPL)

===Proprietary/gratis===
* [http://www.ims.uni-stuttgart.de/tcl/RESOURCES/German-Lexicon-en.html Lexical information for German] ("The data is freely available for education, research and other '''non-commercial''' purposes.")
* [http://www.canoo.net/ Canoo.net] - German Dictionaries and Grammars

===Unknown license===
* [http://www.ims.uni-stuttgart.de/projekte/IMSLex/ IMSLex German Lexicon] (no license information, but only "sample" download)
* [http://www.cl.uzh.ch/CL/siclemat/sprachanalyse/molif/ mOlif morphological analyzer] (broken link)

==Resource Access==
* [http://wortschatz.uni-leipzig.de/Webservices/ Web service access to German language statistics]

==Timeline Analysis==
* [http://wortschatz.uni-leipzig.de/wort-des-tages/ German Words of the Day]
* [http://www.sfs.uni-tuebingen.de/~lothar/nw/ Wortwarte (selection of German neologisms for each day) ]

[[Category:Resources by language|German]]

Resources for Lithuanian

2015-12-17T03:18:24Z

Linas: prototype Lithuanian parser

==Corpora==
* [http://www.statmt.org/europarl Europarl corpus], sentence aligned with English

==Morphological analysis==

* [http://xixona.dlsi.ua.es/wiki/index.php/Incubator#Lithuanian Lithuanian] morphological dictionary from the Apertium project.

==Grammars==

* [http://abisource.com/projects/link-grammar/ Link Grammar Parser], includes prototype Lithuanian dictionaries.

[[Category:Resources by language|Lithuanian]]

Resources for Russian

2014-02-09T02:42:52Z

Linas: /* Grammars */ Link Grammar Parser, includes Russian dictionaries.

==Corpora==
===Free open source===
* [http://www.euromatrixplus.net/multi-un/ MultiUN] "A Multilingual corpus from United Nation Documents", the Russian portion is 876 MB, the other languages in the multilingual corpus are: English/French/Spanish/Arabic/Chinese/German
* [http://www.statmt.org/wmt13/translation-task.html#download WMT corpora], including the Yandex 1M corpus, News Commentary, and News Crawl

===Unknown license===


* [http://www.helsinki.fi/venaja/english/e-material/hanco/index.htm HANCO: The Helsinki annotated corpus of Russian texts] (searchable, no visible download links)
* [http://www.sfb441.uni-tuebingen.de/b1/korpora.html Russian Corpora (uni-tuebingen.de)] (searchable, no visible download links)
* [http://corpus.leeds.ac.uk/ruscorpora.html Russian Internet Corpus]
* [http://www.ruscorpora.ru/ Russian National Corpus]
* [http://www.philol.msu.ru/~lex/corpus/ Russian Newspaper Corpus]
* [http://lib.ru/ Various texts in Russian (lib.ru)]

== POS taggers ==

* [http://www.aot.ru/ AOT, morphological analyser]
* [http://corpus.leeds.ac.uk/mocky/ Mocky, statistical taggers and lemmatiser]
* [http://company.yandex.ru/technology/mystem/ Mystem, morphological analyser]

== Grammars ==
* [[Generation grammars|KPML generation grammar]]
* [http://abisource.com/projects/link-grammar/ Link Grammar Parser], includes Russian dictionaries.

==Various resources==
* [http://rykov-cl.narod.ru/r.html Russian Corpora (rykov-cl.narod.ru)]
* [http://corpus.leeds.ac.uk/serge/frqlist/ Russian frequency lists]
* [http://www.philol.msu.ru/rus/galya-1 Russian Phonetics on the Web]
* [http://schools.keldysh.ru/uvk1838/Sciper/volume2/langres/russiclr.htm Russicon Resources]

[[Category:Resources by language|Russian]]

Downloadable NLG systems

2009-11-19T06:35:25Z

Linas: /* NLGen2 */ it s apache license

The natural language generation systems listed below are available for download over the web.
If you know of a system which is not listed here, please click on Edit in the upper left corner of this page and add the system yourself.

== ASTROGEN ==
http://www.dsv.su.se/~hercules/ASTROGEN/ASTROGEN.html

Aggregated deep and Surface naTuRal language GENerator - Prolog based system.

== CLINT ==
http://www.cs.bgu.ac.il/~elhadad/clint.html

CLINT is a hybrid template / word-based generation system with an example application of
business letter generation. The system is written in C++ and runs under Microsoft Windows.


== CRISP ==
[http://code.google.com/p/crisp-nlg/ CRISP] is Alexander Koller's NLG system that tries to cast both microplanning and sentence realisation as an AI planning problem. The code is a mixture of Java and Scala, a scripting language for the Java virtual machine. CRISP comes with its own implementation of GraphPlan, but it can also output plans in PDDL (“Planning Domain Definition Language”, a successor to STRIPS) for use with other AI planners. License: LGPL.

== FUF/SURGE ==
[http://www.cs.bgu.ac.il/~elhadad/research.html FUF] is available as the [ftp://ftp.cs.bgu.ac.il/pub/fuf/fuf5.3.tar.gz original Common Lisp implementation] and as a C++ port called [http://www.cs.bgu.ac.il/~elhadad/cfuf.zip CFUF] which has an embedded Scheme interpreter.

For more information, see [[#SURGE]], [[#SURGE_2.3]], [[#SURG-SP]], [[#SURG-IT]].

== GenI ==
http://trac.loria.fr/~geni

surface realiser for (Feature-Based Lexicalised) Tree Adjoining Grammar and a flat MRS-like semantics (sans top handle and underspecification). Toy example grammars provided for English and French. Largish core grammar for French is under development (contact us for details). GPL, known to work under Linux and Mac OS X (potential for making it work on Windows as well). Written in Haskell. Source code avalailable via [http://www.darcs.net darcs].

== Grammar Explorer ==
http://www.stir.ac.uk/crcl/Computational-tools/Grexplorer/grexplorer.html

provides a means of exploring large-scale systemic-functional grammars in order to see how they are
organized and what kinds of things they cover. It can be used to explore the KPML resources.
Downloadable standalone executables of the grammar explorer are available for Windows 95/98/NT.
These already include a version of the Nigel grammar of English and pre-installed examples.

== HALogen ==
http://www.isi.edu/licensed-sw/halogen/

HALogen is a general-purpose natural language generation system developed by Irene Langkilde-Geary and Kevin Knight at the USC Information Sciences Institute.
The download package consists of the symbolic generator, the forest ranker, and some sample inputs. The symbolic generator includes the Sensus Ontology dictionary (which is based on WordNet). The forest ranker includes a 250-million word ngram language model (unigram, bigram, and trigram) trained on WSJ newspaper text. The symbolic generator is written in LISP and requires a CommonLisp interpreter.


== KPML ==

http://www.purl.org/net/kpml

The KPML system offers a robust, mature platform for large-scale grammar engineering that is particularly oriented to multilingual grammar development and generation. It is particularly targetted at providing resources for realistic but broad-coverage generation applications, where both flexibility of expression and speed of generation are at issue—for example in online webpage generation or spoken dialogue. KPML is also used extensively in multilingual text generation research and for teaching. It is based on systemic functional linguistics.

The KPML system was a direct descendent of the Penman text generation system, as developed further
multilingually in cooperative work between
the Komet (http://www.darmstadt.gmd.de/publish/komet/index.html)
project in Darmstadt and the Systemic Modelling Group
at Macquarie University. Downloadable standalone executables of the system are available for
PCs running Windows. The source code is written in ANSI Common Lisp and uses the
Common Lisp Interface Manager (CLIM).
The system has been compiled and tested[
under Franz Allegro Common Lisp (4.2, 4.3, 4.3.1, 5.0, 6.0, 7.0)
for Unix and Franz Allegro Common Lisp 3.0
and Harlequin Lispworks 4.0, 4.1, 4.2 for Windows.
It is possible to use the system without the window interface as a generator serving requests for generation across sockets or via files.

A growing set of generation grammars are under development for a variety of languages, inlcluding English, Spanish, Dutch, Chinese, German, Czech, and more. See the
Generation Bank (http://www.fb10.uni-bremen.de/anglistik/langpro/kpml/genbank/generation-bank.html )
for current examples. The development of further languages and of extensions to existing resources are very welcome!

== LKB ==
[http://wiki.delph-in.net/moin/LkbTop LKB] ([[Linguistic Knowledge Builder]]) is a grammar engineering environment for unification-based formalisms, typically HPSG.
It includes a [http://wiki.delph-in.net/moin/LkbGeneration realiser] that takes as input Minimal Recursion Semantics (MRS). LKB is implemented in Common Lisp, and is freely available under an open source license.

== Multimodal Unification Grammar ==
http://www.david-reitter.com/compling/mug/

MUG Workbench is a development and debugging tool for Multimodal NLG. The grammar formalism supported is
Multimodal Functional Unification Grammar (MUG). The MUG system runs MUG grammars with fixed (test cases)
and arbitrary input specifications to produce output in a natural language, graphical user interface and
possibly in other modes. It is designed to do three things:
- Multimodal Fission (distributing output to interaction/communication modes)
- Some sentence planning (chosing information to include in the utterance)
- Natural Language and graphical user interface realization (producing some form of output)
The MUG system does these three jobs in parallel. MUG Workbench can serve to inspect the data-structures
used during generation. It should help you to learn more about the nature of unification grammars used
for parsing or natural language generation. Furthermore, the MUG Workbench is helpful in debugging your grammars.

== NaturalOWL ==
http://www.aueb.gr/users/ion/software/NaturalOWL1.1.tar.gz NaturalOWL (version 1.1)

Generates descriptions of entities and classes from OWL ontologies that have been annotated with linguistic and user modeling resources expressed in RDF. Currently supports English and Greek. Extensions for other languages welcome. NaturalOWL can also be used as a [http://protege.stanford.edu/ Protégé] plug-in. See [http://www.aueb.gr/users/ion/publications.html here] for publications describing NaturalOWL. (GPL)

==NLGen==
The [https://launchpad.net/nlgen NLGen] natural language generation system applies the [http://www.opencog.org/wiki/SegSim SegSim strategy] for generating English sentences. Probabilistic inference for sentence construction is based on a statistical analysis of [http://opencog.org/wiki/RelEx RelEx] output. Not to be confused with NLGen2, below, which uses a different sentence generation theory. Java, Apache license. See demo: [http://novamente.net/example/nlp.html Demo of AI Virtual Pet Answering Simple Questions].

== NLGen2 ==
The [https://launchpad.net/nlgen2 NLGen2] natural language generation system uses [http://opencog.org/wiki/RelEx RelEx] dependency parses, together with [http://www.abisource.com/projects/link-grammar/ Link Grammar] linkage analysis to generate English-language output. Not to be confused with NLGen, above, which uses a different sentence generation theory. Java, Apache license. Reference: Blake Lemoine, "[http://www.louisiana.edu/~bal2277/NLGen2.doc NLGen2: A Linguistically Plausible, General Purpose Natural Language Generation System]".

== OpenCCG ==
[http://openccg.sourceforge.net/ OpenCCG], the OpenNLP CCG Library (formerly Grok), is both a parser and a realizer for [[Combinatory Categorial Grammar]]. It has been used in several dialog systems. The realizer has been enhanced with n-gram models and a supertagging approach called hypertagging. OpenCCG is implemented in Java, and is freely available under the LGPL.

== Project Reporter ==
http://www.cogentex.com/products/reporter

Project Reporter generates dynamic web-based project status reports from files created with Microsoft Project or
other compatible project management software. Reports feature hyperlinked textual descriptions of
project elements, as well as coordinated multimodal display with an interactive Gantt chart applet.
Commercial product. Implemented in Java. Free 30-day evaluation; on-line demo on website.

== RAGS (Reference Architecture for Generation Systems) software ==
http://www.csd.abdn.ac.uk/~cmellish/rags/deliverables/

Deliverables from the RAGS project - RAGSOCKS software for interfacing modules using RAGS data representations,
example RAGS module (genetic algorithm based text planner) and RAGS wrapper for FUF/SURGE.

== RSTTool ==
http://www.dai.ed.ac.uk/staff/personal_pages/micko/RSTTool/

is a tool which allows you to graphically annotate the
rhetorical structure of your text. The structure can be saved in an xml format, or save
eps versions of the structure diagram for inclusion in Latex, etc. Written in Tcl/Tk.
Runs on any machine.

== Simplenlg ==

http://www.csd.abdn.ac.uk/~ereiter/simplenlg

is an ultra-simple Java-based realiser. Its
grammatical coverage and syntactic knowledge is
minuscule compared to KPML or FUF/SURGE.
However, because it is so simple, its relatively
easy for people to learn how to use it. It has
been used by many people in Aberdeen, and also
for teaching. It is set up as a Java package,
so it can only be used by Java programs.

== SPUD ==
[http://www.cs.rutgers.edu/~mdstone/nlg.html SPUD] (Sentence Planner Using Descriptions) is Matthew Purver's LTAG-based NLG system. There are two versions: SPUD version 0.01 was written in SML. Later versions, known as SPUD lite, are written in Prolog. The small codebase of SPUD lite makes it ideal for teaching, but it is also used in dialog system prototypes.

== Suregen-2 ==
[http://www.suregen.de/00023.html Suregen] is “a hybrid, ontology based and NLG-oriented formalism for generating text for documents in clinical medicine.”
The system Suregen-2 is written in (Allegro) Common Lisp. A [http://www.suregen.de/ftp/standalone1.zip demo system] which runs under Windows is available for download. A [http://www.suregen.de/ftp/selfrunningdemo.zip screencast video] shows data being entered into computer forms using mouse and keyboard while a feedback text is continually updated and shown below. (Try playing the AVI file in [http://www.videolan.org/vlc/ VLC] if you run into problems.) Perhaps this system could be considered an instance of the [http://en.wikipedia.org/wiki/WYSIWYM_(Meant) WYSIWYM] approach.

== SURGE ==
http://www.cs.bgu.ac.il/surge/

Syntactic realization package. (A CommonLisp package providing an interpreter for a functional
unification formalism called FUF and SURGE, a large grammar of English written in FUF.) Offers download of SURGE 2.2.

== SURGE 2.3 ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The latest version of Surge, including support for written dialogue, and expanded
syntactic coverage based on the Penn TreeBank.

== SURG-SP ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

Systemic Unification Reusable Grammar for Spanish is a large scale
Spanish grammar allowing systems which already use FUF/SURGE for English NLG to be able
to generate syntactically (and many times semantically) equivalent text in Spanish when
new lexical items are introduced. SURG-SP makes use of inputs almost identical to the
English version Surge 2.3.

== SURG-IT ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The Italian version of Surge 2.3.

== TG/2 ==
http://www.dfki.de/pas/f2w.cgi?lts/tg2-e

is a shallow verbalizer that can be quickly accustomed to new domains and tasks.
It combines context-free grammars with templates and canned
text in a single formalism. Thus the granularity of the language model may depend on the application
needs. The system currently runs under Solaris 2.5. It is available freely under a research license.

[[Category:Software]]
{{SIGGEN Wiki}}

POS Tagging (State of the art)

2009-11-19T05:46:32Z

Linas: /* Table of results */ LTAG-spinal again

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| LTAG-spinal
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ LTAG-spinal]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]
| 96.94% on WSJ, 98.26% on biomed.
|-
|}

== References ==

* Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

* Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

* Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

* Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/pci05.pdf Developing a Robust Part-of-Speech Tagger for Biomedical Text, Advances in Informatics]" - ''10th Panhellenic Conference on Informatics'', '''LNCS 3746''', pp. 382-392, 2005

* Yoshimasa Tsuruoka and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/emnlp05bidir.pdf Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data]", ''Proceedings of HLT/EMNLP 2005'', pp. 467-474.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

POS Tagging (State of the art)

2009-11-19T05:45:57Z

Linas: /* Table of results */ its called "ltag-spinal"

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| POS tagger
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ LTAG-spinal]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]
| 96.94% on WSJ, 98.26% on biomed.
|-
|}

== References ==

* Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

* Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

* Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

* Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/pci05.pdf Developing a Robust Part-of-Speech Tagger for Biomedical Text, Advances in Informatics]" - ''10th Panhellenic Conference on Informatics'', '''LNCS 3746''', pp. 382-392, 2005

* Yoshimasa Tsuruoka and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/emnlp05bidir.pdf Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data]", ''Proceedings of HLT/EMNLP 2005'', pp. 467-474.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

POS Tagging (State of the art)

2009-11-19T05:40:50Z

Linas: /* Table of results */ bad markup

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| POS tagger
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ POS tagger]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]
| 96.94% on WSJ, 98.26% on biomed.
|-
|}

== References ==

* Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

* Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

* Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

* Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/pci05.pdf Developing a Robust Part-of-Speech Tagger for Biomedical Text, Advances in Informatics]" - ''10th Panhellenic Conference on Informatics'', '''LNCS 3746''', pp. 382-392, 2005

* Yoshimasa Tsuruoka and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/emnlp05bidir.pdf Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data]", ''Proceedings of HLT/EMNLP 2005'', pp. 467-474.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

POS Tagging (State of the art)

2009-11-19T05:40:23Z

Linas: /* Table of results */ typo

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| POS tagger
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ POS tagger]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA
| 96.94% on WSJ, 98.26% on biomed.
|-
|}

== References ==

* Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

* Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

* Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

* Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/pci05.pdf Developing a Robust Part-of-Speech Tagger for Biomedical Text, Advances in Informatics]" - ''10th Panhellenic Conference on Informatics'', '''LNCS 3746''', pp. 382-392, 2005

* Yoshimasa Tsuruoka and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/emnlp05bidir.pdf Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data]", ''Proceedings of HLT/EMNLP 2005'', pp. 467-474.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

POS Tagging (State of the art)

2009-11-19T05:39:48Z

Linas: /* References */ bullit points for all refs

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| POS tagger
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ POS tagger]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA
| 96.94% on WSJ, 98.26 on biomed.
|-
|}

== References ==

* Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

* Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

* Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

* Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/pci05.pdf Developing a Robust Part-of-Speech Tagger for Biomedical Text, Advances in Informatics]" - ''10th Panhellenic Conference on Informatics'', '''LNCS 3746''', pp. 382-392, 2005

* Yoshimasa Tsuruoka and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/emnlp05bidir.pdf Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data]", ''Proceedings of HLT/EMNLP 2005'', pp. 467-474.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

POS Tagging (State of the art)

2009-11-19T05:38:50Z

Linas: /* References */ two genia tagger refs

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| POS tagger
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ POS tagger]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA
| 96.94% on WSJ, 98.26 on biomed.
|-
|}

== References ==

Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/pci05.pdf Developing a Robust Part-of-Speech Tagger for Biomedical Text, Advances in Informatics]" - ''10th Panhellenic Conference on Informatics'', '''LNCS 3746''', pp. 382-392, 2005

Yoshimasa Tsuruoka and Jun'ichi Tsujii, "[http://www-tsujii.is.s.u-tokyo.ac.jp/~tsuruoka/papers/emnlp05bidir.pdf Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data]", ''Proceedings of HLT/EMNLP 2005'', pp. 467-474.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

POS Tagging (State of the art)

2009-11-19T05:35:48Z

Linas: /* Table of results */ Genia

* '''Performance measure:''' per token accuracy
* '''Training data:''' sections 0-18 of Wall Street Journal corpus
* '''Testing data:''' sections 22-24 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results
|-
| SVMTool
| SVM-based tagger and tagger generator
| Giménez and Márquez (2004)
| [http://www.lsi.upc.es/~nlp/SVMTool/ SVMTool]
| 97.16%
|-
| Stanford Tagger
| learning with cyclic dependency network
| Toutanova et al. (2003)
| [http://nlp.stanford.edu/software/tagger.shtml Stanford Tagger]
| 97.24%
|-
| POS tagger
| bidirectional perceptron learning
| Shen et al. (2007)
| [http://www.cis.upenn.edu/~xtag/spinal/ POS tagger]
| 97.33%
|-
| GENiA Tagger
| ?
| Tsuruoka, et al (2005)
| [http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA
| 96.94% on WSJ, 98.26 on biomed.
|-
|}

== References ==

Giménez, J., and Márquez, L. (2004). [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.

Shen, L., Satta, G., and Joshi, A. (2007). [http://acl.ldc.upenn.edu/P/P07/P07-1096.pdf Guided learning for bidirectional sequence classification]. ''Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL 2007)'', pages 760-767.

Toutanova, K., Klein, D., Manning, C.D., Yoram Singer, Y. (2003) [http://nlp.stanford.edu/kristina/papers/tagging.pdf Feature-rich part-of-speech tagging with a cyclic dependency network]. ''Proceedings of HLT-NAACL 2003'', pages 252-259.

== See also ==
* [[Part-of-speech tagging]]
* [[State of the art]]

[[Category:State of the art]]

User:Linas

2009-11-19T05:25:15Z

Linas: whhops!

My name is [http://www.linas.org Linas Vepštas]. I am best contacted at [http://en.wikipedia.org/wiki/User:Linas my wikipedia user page]. I maintain the [http://www.abisource.com/projects/link-grammar/ Link Grammar parser], the [http://opencog.org/wiki/RelEx RelEx semantic/dependency relation extractor], and I hack on the NLP subsystem of the [http://opencog.org/ OpenCog] AGI project.

User:Linas

2009-11-19T05:24:38Z

Linas: more about me ...

My name is [http://www.linas.org Linas Vepštas]. I am best contacted at [http://en.wikipedia.org/wiki/User:Linas my wikipedia user page]. I maintain the [http://www.abisource.com/projects/link-grammar/ Link Grammar parser], the [http://opencog.org/wiki/RelEx semantic/dependency relation extractor], and I hack on the NLP subsystem of the [http://opencog.org/ OpenCog] AGI project.

Named entity recognizers

2009-11-19T05:14:20Z

Linas:

'''[[Software]] - Named entity recognizers'''

*[http://balie.sourceforge.net/ Balie] Baseline implementation of named entity recognition.
*[http://gate.ac.uk/ GATE] includes the ANNIE gazeteer-based NER subsystem.
*[http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]- part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text. C++, BSD license.
* [http://www.aueb.gr/users/ion/software/GREEK_NERC_v2.tar.gz Greek named entity recognizer (version 2)] It currently identifies temporal expressions, person names, and organization names; see [http://www.aueb.gr/users/ion/publications.html here] for publications describing the recognizer.
*[http://www.alias-i.com/lingpipe/ LingPipe]
*[http://nlp.stanford.edu/software/CRF-NER.shtml Stanford NER] Conditional Random Fields based NER. Also incorporates distributional similarity based features extracted from the English Gigaword corpus.
*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJNE UIUC NER] Java-based UIUC NER tagger. Uses gazetteers extracted from Wikipedia, word-class model built from unlabeled text and extensively uses non-local features. Achieves 90.8F1 score on the CoNLL03 shared task data and is robust on other datasets. Try the [http://l2r.cs.uiuc.edu/~cogcomp/LbjNer.php LBJ-NER-Demo]
* [http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=NE Older version of UIUC NER] - identifies/classifies entities as Person, Location, Organization and Misc (this last category relates to languages and nationalities); fast and robust; try the [http://l2r.cs.uiuc.edu/~cogcomp/ne_demo.php demo]
[[Category:Software]]

Named entity recognizers

2009-11-19T05:12:36Z

Linas: place into alphabetical order

'''[[Software]] - Named entity recognizers'''

*[http://balie.sourceforge.net/ Balie] Baseline implementation of named entity recognition.
*[http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]- part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text. C++, BSD license.
* [http://www.aueb.gr/users/ion/software/GREEK_NERC_v2.tar.gz Greek named entity recognizer (version 2)] It currently identifies temporal expressions, person names, and organization names; see [http://www.aueb.gr/users/ion/publications.html here] for publications describing the recognizer.
*[http://www.alias-i.com/lingpipe/ LingPipe]
*[http://nlp.stanford.edu/software/CRF-NER.shtml Stanford NER] Conditional Random Fields based NER. Also incorporates distributional similarity based features extracted from the English Gigaword corpus.
*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJNE UIUC NER] Java-based UIUC NER tagger. Uses gazetteers extracted from Wikipedia, word-class model built from unlabeled text and extensively uses non-local features. Achieves 90.8F1 score on the CoNLL03 shared task data and is robust on other datasets. Try the [http://l2r.cs.uiuc.edu/~cogcomp/LbjNer.php LBJ-NER-Demo]
* [http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=NE Older version of UIUC NER] - identifies/classifies entities as Person, Location, Organization and Misc (this last category relates to languages and nationalities); fast and robust; try the [http://l2r.cs.uiuc.edu/~cogcomp/ne_demo.php demo]
[[Category:Software]]

Named entity recognizers

2009-11-19T05:11:21Z

Linas: Add Genia NER

'''[[Software]] - Named entity recognizers'''


*[http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]- part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text. C++, BSD license.
* [http://www.aueb.gr/users/ion/software/GREEK_NERC_v2.tar.gz Greek named entity recognizer (version 2)] It currently identifies temporal expressions, person names, and organization names; see [http://www.aueb.gr/users/ion/publications.html here] for publications describing the recognizer.
*[http://balie.sourceforge.net/ Balie] Baseline implementation of named entity recognition.
*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJNE UIUC NER] Java-based UIUC NER tagger. Uses gazetteers extracted from Wikipedia, word-class model built from unlabeled text and extensively uses non-local features. Achieves 90.8F1 score on the CoNLL03 shared task data and is robust on other datasets. Try the [http://l2r.cs.uiuc.edu/~cogcomp/LbjNer.php LBJ-NER-Demo]
* [http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=NE Older version of UIUC NER] - identifies/classifies entities as Person, Location, Organization and Misc (this last category relates to languages and nationalities); fast and robust; try the [http://l2r.cs.uiuc.edu/~cogcomp/ne_demo.php demo]
*[http://nlp.stanford.edu/software/CRF-NER.shtml Stanford NER] Conditional Random Fields based NER. Also incorporates distributional similarity based features extracted from the English Gigaword corpus.

*[http://www.alias-i.com/lingpipe/ LingPipe]

[[Category:Software]]

Morphology software for English

2009-11-19T05:09:38Z

Linas: /* Free software */ Genia is BSD license, C++

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French -- perl scripts, GPL license
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJPOS LBJ POS Tagger] - Uses averaged perceptron based sequential model. Java API, Free, open source license.
*[http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]- part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text. C++, BSD license.
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

==See also==
*[[Part-of-speech tagging]]

[[Category:Morphology]]
[[Category:Software]]
[[Category:Resources for English]]

Morphology software for English

2009-11-19T05:08:15Z

Linas: /* Part of speech tagging */ add Genia

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French -- perl scripts, GPL license
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://l2r.cs.uiuc.edu/~cogcomp/asoftware.php?skey=FLBJPOS LBJ POS Tagger] - Uses averaged perceptron based sequential model. Java API, Free, open source license.
*[http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/tagger/ GENiA]- part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text.
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

==See also==
*[[Part-of-speech tagging]]

[[Category:Morphology]]
[[Category:Software]]
[[Category:Resources for English]]

NLG publications list

2009-11-19T05:03:05Z

Linas: /* Theses */ Blake Lemoine

If you would like to add your own refereed and NLG-related publications, please go ahead - use the "Edit" link above to do it yourself.

(Correct any broken links if you can - Thanks!)

== Bibliographies ==

* John Bateman and Michael Zock's list of [http://www.fb10.uni-bremen.de/anglistik/langpro/NLG-table/NLG-table-root.htm NLG systems] and associated references.
* John Bateman's Bibliography site [http://www.fb10.uni-bremen.de/anglistik/langpro/bibliographies/index.htm] contains a superset of the references used in the above list of NLG systems, including references for all aspects of NLG. Particular sub-bibliographies can be generated on demand. There are over 3000 entries concerning NLG and updates are welcome. The bibliography is maintained in [[BibTeX]] and is linked to/maintained at the Collection of Computer Science Bibliographies with its extensive cross-linking and search facilities.
* A 1993 bibliography of ~1200 entries provided by [http://www.kantrowitz.com:80/kantrowitz/mark.html Mark Kantrowitz] [http://liinwww.ira.uka.de/bibliography/Ai/nlg.html On-line searchable version] ([ftp://ftp.cs.bgu.ac.il/pub/siggen/kbib/nlg-bib.ps.gz ps.gz] 126K, 49 pages, [ftp://ftp.cs.bgu.ac.il/pub/siggen/kbib/nlg-bib.dvi.gz dvi.gz] 109K, [ftp://ftp.cs.bgu.ac.il/pub/siggen/kbib/nlg.bib.gz BIBTEX source bib.gz] 72K) Mark Kantrowitz, "Bibliography of Research in Natural Language Generation", Techical Report CMU-CS-93-216, Carnegie Mellon University, November 1993.
* A 1990 annotated bibliography provided by Robert Dale, 27 pages ([ftp://ftp.cs.bgu.ac.il/pub/siggen/dbib/IntroToNLG-[[RefList]].ps.gz ps.gz] 70K, [ftp://ftp.cs.bgu.ac.il/pub/siggen/dbib/IntroToNLG-[[RefList]].tex.gz [[LaTeX]] source tex.gz] 70K)
* A 1993 revision of Dale's bibliography, 50 pages ([ftp://ftp.cs.bgu.ac.il/pub/siggen/dbib/nlgbiblio2.01a4.ps.gz ps.gz] 100K)
* Aggeliki Dimitromanolaki's [http://www.iit.demokritos.gr/~adimit/bibliography.html bibliography on machine learning and natural language generation]
* Piwek, P. (2003). An Annotated Bibliography of Affective Natural Language Generation. version 1.3 (version 1.0 appeared in 2002 as ITRI Technical Report ITRI-02-02, University of Brighton). [http://mcs.open.ac.uk/pp2464/affect-bib.pdf pdf]
* Piwek, P. and K. van Deemter (2006). Constraint-based Natural Language Generation: A Survey. Technical Report 2006/03, Computing Department, The Open University. [http://mcs.open.ac.uk/pp2464/constraints_survey.pdf pdf] [http://mcs.open.ac.uk/pp2464/constraints_in_nlg.bib bib]

== Tutorials ==

* Dale & Reiter's ANLP-97 Tutorial on Building Applied Natural Language Generation Systems. ([http://www.csd.abdn.ac.uk/~ereiter/papers/tut-ppt7.ppt.gz PPT7]) ([http://www.csd.abdn.ac.uk/~ereiter/papers/tut-ppt4.ppt.gz PPT4]) ([http://www.csd.abdn.ac.uk/~ereiter/papers/tut.ps.gz Postscript])
* Emiel Krahmer and Paul Piwek. Natural Language Generation for Embodied Agents. At the 7th European Agent Systems Summer School (EASSS) (July 2005, Utrecht). [http://mcs.open.ac.uk/pp2464/easss05 course material]

== Theses ==

* Charles Callaway, Narrative Prose Generation, Ph.D. Thesis, Department of Computer Science, North Carolina State University, April 2000. [http://homepages.inf.ed.ac.uk/ccallawa/pubs.html#dissertation web page]
* Giuseppe Carenini, Generating and Evaluating Evaluative Arguments, Ph.D. Thesis, Department of Computer Science, University of Pittsburgh, 2000. [http://www.cs.ubc.ca/~carenini/THESIS/thesis-page.html web page]
* Hercules Dalianis, Concise Natural Language Generation from Formal Specifications, Ph.D. Thesis, (Teknologie Doktorsavhandling), Department of Computer and Systems Sciences, Royal Institute of Technology, Stockholm University, June 1996, Report Series No. 96-008, ISSN 1101-8526, SRN SU-KTH/DSV/R--96/8--SE. [http://www.cs.bgu.ac.il/siggen/abstracts.html#dalianis-phd Abstract]
* Michael Elhadad, Using argumentation to control lexical choice: a unification-based implementation, PhD thesis, Columbia University, Dept of Computer Science, 1993, [ftp://ftp.cs.bgu.ac.il/pub/siggen/elhadad-phd.ps.gz ps gzipped] (575K).
* Blake Lemoine, ''[http://www.louisiana.edu/~bal2277/NLGen2.doc NLGen2: A Linguistically Plausible, General Purpose Natural Language Generation System]'', August 2009, Center for Advanced Computer Studies, University of Louisiana, Lafayette. Excerpt from Master's thesis.
* Maria Milosavljevic. The Automatic Generation of Comparisons in Descriptions of Entities. PhD Thesis. Department of Computing, Macquarie University. February 1999. [http://www.comp.mq.edu.au/~mariam/papers/thesis/thesis.pdf pdf], [http://www.comp.mq.edu.au/~mariam/papers/thesis/thesis.ps.gz ps.gz]
* Jacques Robin, Revision-based generation of natural language summaries providing historical background: corpus-based analysis, design, implementation and evaluation, PhD thesis, Columbia University, Dept of Computer Science, 1994, [ftp://ftp.cs.bgu.ac.il/pub/siggen/robin-phd.ps.gz ps gzipped] (762K).
* Manfred Stede, Lexical semantics and knowledge representation in multilingual sentence generation, PhD thesis, Department of Computer Science, University of Toronto, 1996, Technical report CSRI-347, [http://www.cs.bgu.ac.il/siggen/abstracts.html#stede-phd Abstract], [ftp://ftp.cs.bgu.ac.il/pub/siggen/stede-phd.ps.gz ps gz] (384K), [ftp://ftp.cs.utoronto.ca/csri-technical-reports/347/Stede-thesis.ps.gz ps gz Toronto], [ftp://ftp.cs.utoronto.ca/csri-technical-reports/347/Stede-thesis.ps ps Toronto] (1292K).
* Mariet Theune, From data to speech: language generation in context, PhD thesis, University of Eindhoven, The Netherlands, 2000. [http://alexandria.tue.nl/extra2/200013408.pdf pdf]

== Natural Language Generation Workshops ==

'Note': Proceedings of many NLG workshops
are available at the
[http://www.aclweb.org/anthology ACL Anthology]
* [http://acl.ldc.upenn.edu/W/SIGGEN.html SIGGEN] contains proceedings of INLG 1990, 1994, 1996, 1998, 2000
* [http://acl.ldc.upenn.edu/W/W05 workshops05] contains proceedings of ENLG 2005
* [http://acl.ldc.upenn.edu/W/W06/ workshops06] contains proceedings of INLG 2006

=== 1992 International NLGW ===

* Michael Elhadad and Jacques Robin, Controlling Content Realization with Functional Unification Grammars, in <var>Aspects of Automated Natural Language Generation</var><nowiki>; R. Dale, E. Hovy, D. Rosner and O. Stock editors, 89-104, Springer Verlag, 1992. (16 pages: 53K </nowiki>[ftp://ftp.cs.bgu.ac.il/pub/people/elhadad/control.ps.gz ps gz], 62K [ftp://ftp.cs.bgu.ac.il/pub/people/elhadad/control.dvi dvi])

=== 1994 International NLGW ===

* Beryl Hoffman, Generating Context-Appropriate Word Orders in Turkish, [http://www.cs.bgu.ac.il/siggen/abstracts.html#inlg94-hoffman Abstract], [http://xxx.lanl.gov/abs/cmp-lg/9407017 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg94-hoffman.ps.gz ps gz] (53K)
* Franck Panaget, Using a textual representational level component in the context of discourse or dialog generation, [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg94-panaget.ps.gz ps gz] (10 pages, 57K)
* E. Reiter, Has a Consensus NLG Architecture Appeared, and is it Psycholinguistically Plausible?, [http://www.cs.bgu.ac.il/siggen/abstracts.html#inlg94-reiter Abstract], [http://xxx.lanl.gov/abs/cmp-lg/9411032 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg94-reiter.ps.gz ps gz] (56K)
* R. Michael Young and Johanna D. Moore, DPOCL: A Principled Approach to Discourse Planning, [http://www.cs.bgu.ac.il/siggen/abstracts.html#inlg94-young Abstract], 8 pages, [http://xxx.lanl.gov/abs/cmp-lg/9406020 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg94-young.ps.gz ps gz] (52K)

=== 1995 European NLGW ===

* Brigitte Grote, Nils Lenke and Manfred Stede, Ma(r)king concessions in English and German, (23 pages, [http://www.cs.bgu.ac.il/siggen/abstracts.html#enlg95-grote Abstract], [http://xxx.lanl.gov/abs/cmp-lg/9506001 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/enlg95-grote.ps.gz ps gz] 147K)
* E. Reiter, NLG vs Templates, [http://www.cs.bgu.ac.il/siggen/abstracts.html#enlg95-reiter (Abstract], [http://xxx.lanl.gov/abs/cmp-lg/9504013 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/enlg95-reiter.ps.gz ps gz] 113K)
* Michael White, Presenting Punctuation, [http://www.cs.bgu.ac.il/siggen/abstracts.html#enlg95-white (Abstract], [http://xxx.lanl.gov/abs/cmp-lg/9506012 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/enlg95-white.ps.gz ps gz] 113K, 19 pages)

=== 1996 International NLGW (Brighton) ===
([http://www.itri.brighton.ac.uk/events/INLG-96/ Link])

* Stephan Busemann, Best-First Surface Realization, [http://www.cs.bgu.ac.il/siggen/abstracts.html#inlg96-busemann Abstract], 10 pages, 60K, [http://xxx.lanl.gov/abs/cmp-lg/9605010 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg96-busemann.ps.gz ps gz]
* H. Dalianis and E, Hovy, On Lexical Aggregation and Ordering (Demo), [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg96-dalianis.ps.gz ps gz] (14K) or [http://www.dsv.su.se/~hercules/INLG96.html alternate]
* Michael Elhadad & Jacques Robin (Demo) An Overview of SURGE: A reusable comprehensive syntactic realization component (10 pages, 55K [ftp://ftp.cs.bgu.ac.il/pub/people/elhadad/surge.dvi dvi], [ftp://ftp.cs.bgu.ac.il/pub/people/elhadad/surge.ps.gz ps gz])
* Dilek Zeynep Hakkani, Kemal Oflazer and Ilyas Cicekli, Tactical Generation in a Free Constituent Order Language, [http://www.cs.bgu.ac.il/siggen/abstracts.html#inlg96-hakkani Abstract], 10 pages, 57K, [http://xxx.lanl.gov/abs/cmp-lg/9605008 cmp-lg], [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg96-hakkani.ps.gz ps gz]
* Keith Vander Linden and Barbara Di Eugenio, Learning Micro-Planning Rules for Preventative Expressions, [http://www.cs.bgu.ac.il/siggen/abstracts.html#inlg96-vanderlinden Abstract], 8 pages, 95K, [ftp://ftp.cs.bgu.ac.il/pub/siggen/inlg96-vanderlinden.ps.gz ps gz], [http://xxx.lanl.gov/abs/cmp-lg/9607015 cmp-lg]

=== UCNLG 2005 ===
Anja Belz and Sebastian Varges (eds). Proceedings of the Corpus Linguistics 2005Workshop on Using Corpora for Natural Language Generation. Available [http://www.itri.brighton.ac.uk/ucnlg/Proceedings/index.html individually] or as a single [http://www.itri.brighton.ac.uk/~Anja.Belz/Publications/UCNLG05-proceedings.pdf PDF] file.

=== INLG'06 Special Session on Sharing Data and Comparative Evaluation ===
See [[Sharing data and evaluation (NLG)]].

=== MOG 2007 ===
Ielka van der Sluis, Mariët Theune, Ehud Reiter & Emiel Krahmer (eds). Proceedings of the Workshop on Multimodal Output Generation (MOG 2007). 25-26 January 2007, Aberdeen, Scotland. [http://www.csd.abdn.ac.uk/mog2007/mog07_proceedings.pdf PDF].

[[Category:Bibliographies]]
{{SIGGEN Wiki}}

Downloadable NLG systems

2009-11-19T04:57:27Z

Linas: /* NLGen2 */ java open source

The natural language generation systems listed below are available for download over the web.
If you know of a system which is not listed here, please click on Edit in the upper left corner of this page and add the system yourself.

== ASTROGEN ==
http://www.dsv.su.se/~hercules/ASTROGEN/ASTROGEN.html

Aggregated deep and Surface naTuRal language GENerator - Prolog based system.

== CLINT ==
http://www.cs.bgu.ac.il/~elhadad/clint.html

CLINT is a hybrid template / word-based generation system with an example application of
business letter generation. The system is written in C++ and runs under Microsoft Windows.


== CRISP ==
[http://code.google.com/p/crisp-nlg/ CRISP] is Alexander Koller's NLG system that tries to cast both microplanning and sentence realisation as an AI planning problem. The code is a mixture of Java and Scala, a scripting language for the Java virtual machine. CRISP comes with its own implementation of GraphPlan, but it can also output plans in PDDL (“Planning Domain Definition Language”, a successor to STRIPS) for use with other AI planners. License: LGPL.

== FUF/SURGE ==
[http://www.cs.bgu.ac.il/~elhadad/research.html FUF] is available as the [ftp://ftp.cs.bgu.ac.il/pub/fuf/fuf5.3.tar.gz original Common Lisp implementation] and as a C++ port called [http://www.cs.bgu.ac.il/~elhadad/cfuf.zip CFUF] which has an embedded Scheme interpreter.

For more information, see [[#SURGE]], [[#SURGE_2.3]], [[#SURG-SP]], [[#SURG-IT]].

== GenI ==
http://trac.loria.fr/~geni

surface realiser for (Feature-Based Lexicalised) Tree Adjoining Grammar and a flat MRS-like semantics (sans top handle and underspecification). Toy example grammars provided for English and French. Largish core grammar for French is under development (contact us for details). GPL, known to work under Linux and Mac OS X (potential for making it work on Windows as well). Written in Haskell. Source code avalailable via [http://www.darcs.net darcs].

== Grammar Explorer ==
http://www.stir.ac.uk/crcl/Computational-tools/Grexplorer/grexplorer.html

provides a means of exploring large-scale systemic-functional grammars in order to see how they are
organized and what kinds of things they cover. It can be used to explore the KPML resources.
Downloadable standalone executables of the grammar explorer are available for Windows 95/98/NT.
These already include a version of the Nigel grammar of English and pre-installed examples.

== HALogen ==
http://www.isi.edu/licensed-sw/halogen/

HALogen is a general-purpose natural language generation system developed by Irene Langkilde-Geary and Kevin Knight at the USC Information Sciences Institute.
The download package consists of the symbolic generator, the forest ranker, and some sample inputs. The symbolic generator includes the Sensus Ontology dictionary (which is based on WordNet). The forest ranker includes a 250-million word ngram language model (unigram, bigram, and trigram) trained on WSJ newspaper text. The symbolic generator is written in LISP and requires a CommonLisp interpreter.


== KPML ==

http://www.purl.org/net/kpml

The KPML system offers a robust, mature platform for large-scale grammar engineering that is particularly oriented to multilingual grammar development and generation. It is particularly targetted at providing resources for realistic but broad-coverage generation applications, where both flexibility of expression and speed of generation are at issue—for example in online webpage generation or spoken dialogue. KPML is also used extensively in multilingual text generation research and for teaching. It is based on systemic functional linguistics.

The KPML system was a direct descendent of the Penman text generation system, as developed further
multilingually in cooperative work between
the Komet (http://www.darmstadt.gmd.de/publish/komet/index.html)
project in Darmstadt and the Systemic Modelling Group
at Macquarie University. Downloadable standalone executables of the system are available for
PCs running Windows. The source code is written in ANSI Common Lisp and uses the
Common Lisp Interface Manager (CLIM).
The system has been compiled and tested[
under Franz Allegro Common Lisp (4.2, 4.3, 4.3.1, 5.0, 6.0, 7.0)
for Unix and Franz Allegro Common Lisp 3.0
and Harlequin Lispworks 4.0, 4.1, 4.2 for Windows.
It is possible to use the system without the window interface as a generator serving requests for generation across sockets or via files.

A growing set of generation grammars are under development for a variety of languages, inlcluding English, Spanish, Dutch, Chinese, German, Czech, and more. See the
Generation Bank (http://www.fb10.uni-bremen.de/anglistik/langpro/kpml/genbank/generation-bank.html )
for current examples. The development of further languages and of extensions to existing resources are very welcome!

== LKB ==
[http://wiki.delph-in.net/moin/LkbTop LKB] ([[Linguistic Knowledge Builder]]) is a grammar engineering environment for unification-based formalisms, typically HPSG.
It includes a [http://wiki.delph-in.net/moin/LkbGeneration realiser] that takes as input Minimal Recursion Semantics (MRS). LKB is implemented in Common Lisp, and is freely available under an open source license.

== Multimodal Unification Grammar ==
http://www.david-reitter.com/compling/mug/

MUG Workbench is a development and debugging tool for Multimodal NLG. The grammar formalism supported is
Multimodal Functional Unification Grammar (MUG). The MUG system runs MUG grammars with fixed (test cases)
and arbitrary input specifications to produce output in a natural language, graphical user interface and
possibly in other modes. It is designed to do three things:
- Multimodal Fission (distributing output to interaction/communication modes)
- Some sentence planning (chosing information to include in the utterance)
- Natural Language and graphical user interface realization (producing some form of output)
The MUG system does these three jobs in parallel. MUG Workbench can serve to inspect the data-structures
used during generation. It should help you to learn more about the nature of unification grammars used
for parsing or natural language generation. Furthermore, the MUG Workbench is helpful in debugging your grammars.

== NaturalOWL ==
http://www.aueb.gr/users/ion/software/NaturalOWL1.1.tar.gz NaturalOWL (version 1.1)

Generates descriptions of entities and classes from OWL ontologies that have been annotated with linguistic and user modeling resources expressed in RDF. Currently supports English and Greek. Extensions for other languages welcome. NaturalOWL can also be used as a [http://protege.stanford.edu/ Protégé] plug-in. See [http://www.aueb.gr/users/ion/publications.html here] for publications describing NaturalOWL. (GPL)

==NLGen==
The [https://launchpad.net/nlgen NLGen] natural language generation system applies the [http://www.opencog.org/wiki/SegSim SegSim strategy] for generating English sentences. Probabilistic inference for sentence construction is based on a statistical analysis of [http://opencog.org/wiki/RelEx RelEx] output. Not to be confused with NLGen2, below, which uses a different sentence generation theory. Java, Apache license. See demo: [http://novamente.net/example/nlp.html Demo of AI Virtual Pet Answering Simple Questions].

== NLGen2 ==
The [https://launchpad.net/nlgen2 NLGen2] natural language generation system uses [http://opencog.org/wiki/RelEx RelEx] dependency parses, together with [http://www.abisource.com/projects/link-grammar/ Link Grammar] linkage analysis to generate English-language output. Not to be confused with NLGen, above, which uses a different sentence generation theory. Java, open source. Reference: Blake Lemoine, "[http://www.louisiana.edu/~bal2277/NLGen2.doc NLGen2: A Linguistically Plausible, General Purpose Natural Language Generation System]".

== OpenCCG ==
[http://openccg.sourceforge.net/ OpenCCG], the OpenNLP CCG Library (formerly Grok), is both a parser and a realizer for [[Combinatory Categorial Grammar]]. It has been used in several dialog systems. The realizer has been enhanced with n-gram models and a supertagging approach called hypertagging. OpenCCG is implemented in Java, and is freely available under the LGPL.

== Project Reporter ==
http://www.cogentex.com/products/reporter

Project Reporter generates dynamic web-based project status reports from files created with Microsoft Project or
other compatible project management software. Reports feature hyperlinked textual descriptions of
project elements, as well as coordinated multimodal display with an interactive Gantt chart applet.
Commercial product. Implemented in Java. Free 30-day evaluation; on-line demo on website.

== RAGS (Reference Architecture for Generation Systems) software ==
http://www.csd.abdn.ac.uk/~cmellish/rags/deliverables/

Deliverables from the RAGS project - RAGSOCKS software for interfacing modules using RAGS data representations,
example RAGS module (genetic algorithm based text planner) and RAGS wrapper for FUF/SURGE.

== RSTTool ==
http://www.dai.ed.ac.uk/staff/personal_pages/micko/RSTTool/

is a tool which allows you to graphically annotate the
rhetorical structure of your text. The structure can be saved in an xml format, or save
eps versions of the structure diagram for inclusion in Latex, etc. Written in Tcl/Tk.
Runs on any machine.

== Simplenlg ==

http://www.csd.abdn.ac.uk/~ereiter/simplenlg

is an ultra-simple Java-based realiser. Its
grammatical coverage and syntactic knowledge is
minuscule compared to KPML or FUF/SURGE.
However, because it is so simple, its relatively
easy for people to learn how to use it. It has
been used by many people in Aberdeen, and also
for teaching. It is set up as a Java package,
so it can only be used by Java programs.

== SPUD ==
[http://www.cs.rutgers.edu/~mdstone/nlg.html SPUD] (Sentence Planner Using Descriptions) is Matthew Purver's LTAG-based NLG system. There are two versions: SPUD version 0.01 was written in SML. Later versions, known as SPUD lite, are written in Prolog. The small codebase of SPUD lite makes it ideal for teaching, but it is also used in dialog system prototypes.

== Suregen-2 ==
[http://www.suregen.de/00023.html Suregen] is “a hybrid, ontology based and NLG-oriented formalism for generating text for documents in clinical medicine.”
The system Suregen-2 is written in (Allegro) Common Lisp. A [http://www.suregen.de/ftp/standalone1.zip demo system] which runs under Windows is available for download. A [http://www.suregen.de/ftp/selfrunningdemo.zip screencast video] shows data being entered into computer forms using mouse and keyboard while a feedback text is continually updated and shown below. (Try playing the AVI file in [http://www.videolan.org/vlc/ VLC] if you run into problems.) Perhaps this system could be considered an instance of the [http://en.wikipedia.org/wiki/WYSIWYM_(Meant) WYSIWYM] approach.

== SURGE ==
http://www.cs.bgu.ac.il/surge/

Syntactic realization package. (A CommonLisp package providing an interpreter for a functional
unification formalism called FUF and SURGE, a large grammar of English written in FUF.) Offers download of SURGE 2.2.

== SURGE 2.3 ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The latest version of Surge, including support for written dialogue, and expanded
syntactic coverage based on the Penn TreeBank.

== SURG-SP ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

Systemic Unification Reusable Grammar for Spanish is a large scale
Spanish grammar allowing systems which already use FUF/SURGE for English NLG to be able
to generate syntactically (and many times semantically) equivalent text in Spanish when
new lexical items are introduced. SURG-SP makes use of inputs almost identical to the
English version Surge 2.3.

== SURG-IT ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The Italian version of Surge 2.3.

== TG/2 ==
http://www.dfki.de/pas/f2w.cgi?lts/tg2-e

is a shallow verbalizer that can be quickly accustomed to new domains and tasks.
It combines context-free grammars with templates and canned
text in a single formalism. Thus the granularity of the language model may depend on the application
needs. The system currently runs under Solaris 2.5. It is available freely under a research license.

[[Category:Software]]
{{SIGGEN Wiki}}

Downloadable NLG systems

2009-11-19T04:56:58Z

Linas: /* NLGen */

The natural language generation systems listed below are available for download over the web.
If you know of a system which is not listed here, please click on Edit in the upper left corner of this page and add the system yourself.

== ASTROGEN ==
http://www.dsv.su.se/~hercules/ASTROGEN/ASTROGEN.html

Aggregated deep and Surface naTuRal language GENerator - Prolog based system.

== CLINT ==
http://www.cs.bgu.ac.il/~elhadad/clint.html

CLINT is a hybrid template / word-based generation system with an example application of
business letter generation. The system is written in C++ and runs under Microsoft Windows.


== CRISP ==
[http://code.google.com/p/crisp-nlg/ CRISP] is Alexander Koller's NLG system that tries to cast both microplanning and sentence realisation as an AI planning problem. The code is a mixture of Java and Scala, a scripting language for the Java virtual machine. CRISP comes with its own implementation of GraphPlan, but it can also output plans in PDDL (“Planning Domain Definition Language”, a successor to STRIPS) for use with other AI planners. License: LGPL.

== FUF/SURGE ==
[http://www.cs.bgu.ac.il/~elhadad/research.html FUF] is available as the [ftp://ftp.cs.bgu.ac.il/pub/fuf/fuf5.3.tar.gz original Common Lisp implementation] and as a C++ port called [http://www.cs.bgu.ac.il/~elhadad/cfuf.zip CFUF] which has an embedded Scheme interpreter.

For more information, see [[#SURGE]], [[#SURGE_2.3]], [[#SURG-SP]], [[#SURG-IT]].

== GenI ==
http://trac.loria.fr/~geni

surface realiser for (Feature-Based Lexicalised) Tree Adjoining Grammar and a flat MRS-like semantics (sans top handle and underspecification). Toy example grammars provided for English and French. Largish core grammar for French is under development (contact us for details). GPL, known to work under Linux and Mac OS X (potential for making it work on Windows as well). Written in Haskell. Source code avalailable via [http://www.darcs.net darcs].

== Grammar Explorer ==
http://www.stir.ac.uk/crcl/Computational-tools/Grexplorer/grexplorer.html

provides a means of exploring large-scale systemic-functional grammars in order to see how they are
organized and what kinds of things they cover. It can be used to explore the KPML resources.
Downloadable standalone executables of the grammar explorer are available for Windows 95/98/NT.
These already include a version of the Nigel grammar of English and pre-installed examples.

== HALogen ==
http://www.isi.edu/licensed-sw/halogen/

HALogen is a general-purpose natural language generation system developed by Irene Langkilde-Geary and Kevin Knight at the USC Information Sciences Institute.
The download package consists of the symbolic generator, the forest ranker, and some sample inputs. The symbolic generator includes the Sensus Ontology dictionary (which is based on WordNet). The forest ranker includes a 250-million word ngram language model (unigram, bigram, and trigram) trained on WSJ newspaper text. The symbolic generator is written in LISP and requires a CommonLisp interpreter.


== KPML ==

http://www.purl.org/net/kpml

The KPML system offers a robust, mature platform for large-scale grammar engineering that is particularly oriented to multilingual grammar development and generation. It is particularly targetted at providing resources for realistic but broad-coverage generation applications, where both flexibility of expression and speed of generation are at issue—for example in online webpage generation or spoken dialogue. KPML is also used extensively in multilingual text generation research and for teaching. It is based on systemic functional linguistics.

The KPML system was a direct descendent of the Penman text generation system, as developed further
multilingually in cooperative work between
the Komet (http://www.darmstadt.gmd.de/publish/komet/index.html)
project in Darmstadt and the Systemic Modelling Group
at Macquarie University. Downloadable standalone executables of the system are available for
PCs running Windows. The source code is written in ANSI Common Lisp and uses the
Common Lisp Interface Manager (CLIM).
The system has been compiled and tested[
under Franz Allegro Common Lisp (4.2, 4.3, 4.3.1, 5.0, 6.0, 7.0)
for Unix and Franz Allegro Common Lisp 3.0
and Harlequin Lispworks 4.0, 4.1, 4.2 for Windows.
It is possible to use the system without the window interface as a generator serving requests for generation across sockets or via files.

A growing set of generation grammars are under development for a variety of languages, inlcluding English, Spanish, Dutch, Chinese, German, Czech, and more. See the
Generation Bank (http://www.fb10.uni-bremen.de/anglistik/langpro/kpml/genbank/generation-bank.html )
for current examples. The development of further languages and of extensions to existing resources are very welcome!

== LKB ==
[http://wiki.delph-in.net/moin/LkbTop LKB] ([[Linguistic Knowledge Builder]]) is a grammar engineering environment for unification-based formalisms, typically HPSG.
It includes a [http://wiki.delph-in.net/moin/LkbGeneration realiser] that takes as input Minimal Recursion Semantics (MRS). LKB is implemented in Common Lisp, and is freely available under an open source license.

== Multimodal Unification Grammar ==
http://www.david-reitter.com/compling/mug/

MUG Workbench is a development and debugging tool for Multimodal NLG. The grammar formalism supported is
Multimodal Functional Unification Grammar (MUG). The MUG system runs MUG grammars with fixed (test cases)
and arbitrary input specifications to produce output in a natural language, graphical user interface and
possibly in other modes. It is designed to do three things:
- Multimodal Fission (distributing output to interaction/communication modes)
- Some sentence planning (chosing information to include in the utterance)
- Natural Language and graphical user interface realization (producing some form of output)
The MUG system does these three jobs in parallel. MUG Workbench can serve to inspect the data-structures
used during generation. It should help you to learn more about the nature of unification grammars used
for parsing or natural language generation. Furthermore, the MUG Workbench is helpful in debugging your grammars.

== NaturalOWL ==
http://www.aueb.gr/users/ion/software/NaturalOWL1.1.tar.gz NaturalOWL (version 1.1)

Generates descriptions of entities and classes from OWL ontologies that have been annotated with linguistic and user modeling resources expressed in RDF. Currently supports English and Greek. Extensions for other languages welcome. NaturalOWL can also be used as a [http://protege.stanford.edu/ Protégé] plug-in. See [http://www.aueb.gr/users/ion/publications.html here] for publications describing NaturalOWL. (GPL)

==NLGen==
The [https://launchpad.net/nlgen NLGen] natural language generation system applies the [http://www.opencog.org/wiki/SegSim SegSim strategy] for generating English sentences. Probabilistic inference for sentence construction is based on a statistical analysis of [http://opencog.org/wiki/RelEx RelEx] output. Not to be confused with NLGen2, below, which uses a different sentence generation theory. Java, Apache license. See demo: [http://novamente.net/example/nlp.html Demo of AI Virtual Pet Answering Simple Questions].

== NLGen2 ==
The [https://launchpad.net/nlgen2 NLGen2] natural language generation system uses [http://opencog.org/wiki/RelEx RelEx] dependency parses, together with [http://www.abisource.com/projects/link-grammar/ Link Grammar] linkage analysis to generate English-language output. Not to be confused with NLGen, above, which uses a different sentence generation theory. Reference: Blake Lemoine, "[http://www.louisiana.edu/~bal2277/NLGen2.doc NLGen2: A Linguistically Plausible, General Purpose Natural Language Generation System]".

== OpenCCG ==
[http://openccg.sourceforge.net/ OpenCCG], the OpenNLP CCG Library (formerly Grok), is both a parser and a realizer for [[Combinatory Categorial Grammar]]. It has been used in several dialog systems. The realizer has been enhanced with n-gram models and a supertagging approach called hypertagging. OpenCCG is implemented in Java, and is freely available under the LGPL.

== Project Reporter ==
http://www.cogentex.com/products/reporter

Project Reporter generates dynamic web-based project status reports from files created with Microsoft Project or
other compatible project management software. Reports feature hyperlinked textual descriptions of
project elements, as well as coordinated multimodal display with an interactive Gantt chart applet.
Commercial product. Implemented in Java. Free 30-day evaluation; on-line demo on website.

== RAGS (Reference Architecture for Generation Systems) software ==
http://www.csd.abdn.ac.uk/~cmellish/rags/deliverables/

Deliverables from the RAGS project - RAGSOCKS software for interfacing modules using RAGS data representations,
example RAGS module (genetic algorithm based text planner) and RAGS wrapper for FUF/SURGE.

== RSTTool ==
http://www.dai.ed.ac.uk/staff/personal_pages/micko/RSTTool/

is a tool which allows you to graphically annotate the
rhetorical structure of your text. The structure can be saved in an xml format, or save
eps versions of the structure diagram for inclusion in Latex, etc. Written in Tcl/Tk.
Runs on any machine.

== Simplenlg ==

http://www.csd.abdn.ac.uk/~ereiter/simplenlg

is an ultra-simple Java-based realiser. Its
grammatical coverage and syntactic knowledge is
minuscule compared to KPML or FUF/SURGE.
However, because it is so simple, its relatively
easy for people to learn how to use it. It has
been used by many people in Aberdeen, and also
for teaching. It is set up as a Java package,
so it can only be used by Java programs.

== SPUD ==
[http://www.cs.rutgers.edu/~mdstone/nlg.html SPUD] (Sentence Planner Using Descriptions) is Matthew Purver's LTAG-based NLG system. There are two versions: SPUD version 0.01 was written in SML. Later versions, known as SPUD lite, are written in Prolog. The small codebase of SPUD lite makes it ideal for teaching, but it is also used in dialog system prototypes.

== Suregen-2 ==
[http://www.suregen.de/00023.html Suregen] is “a hybrid, ontology based and NLG-oriented formalism for generating text for documents in clinical medicine.”
The system Suregen-2 is written in (Allegro) Common Lisp. A [http://www.suregen.de/ftp/standalone1.zip demo system] which runs under Windows is available for download. A [http://www.suregen.de/ftp/selfrunningdemo.zip screencast video] shows data being entered into computer forms using mouse and keyboard while a feedback text is continually updated and shown below. (Try playing the AVI file in [http://www.videolan.org/vlc/ VLC] if you run into problems.) Perhaps this system could be considered an instance of the [http://en.wikipedia.org/wiki/WYSIWYM_(Meant) WYSIWYM] approach.

== SURGE ==
http://www.cs.bgu.ac.il/surge/

Syntactic realization package. (A CommonLisp package providing an interpreter for a functional
unification formalism called FUF and SURGE, a large grammar of English written in FUF.) Offers download of SURGE 2.2.

== SURGE 2.3 ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The latest version of Surge, including support for written dialogue, and expanded
syntactic coverage based on the Penn TreeBank.

== SURG-SP ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

Systemic Unification Reusable Grammar for Spanish is a large scale
Spanish grammar allowing systems which already use FUF/SURGE for English NLG to be able
to generate syntactically (and many times semantically) equivalent text in Spanish when
new lexical items are introduced. SURG-SP makes use of inputs almost identical to the
English version Surge 2.3.

== SURG-IT ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The Italian version of Surge 2.3.

== TG/2 ==
http://www.dfki.de/pas/f2w.cgi?lts/tg2-e

is a shallow verbalizer that can be quickly accustomed to new domains and tasks.
It combines context-free grammars with templates and canned
text in a single formalism. Thus the granularity of the language model may depend on the application
needs. The system currently runs under Solaris 2.5. It is available freely under a research license.

[[Category:Software]]
{{SIGGEN Wiki}}

Downloadable NLG systems

2009-11-19T04:54:36Z

Linas: NLGen and NLGen2

The natural language generation systems listed below are available for download over the web.
If you know of a system which is not listed here, please click on Edit in the upper left corner of this page and add the system yourself.

== ASTROGEN ==
http://www.dsv.su.se/~hercules/ASTROGEN/ASTROGEN.html

Aggregated deep and Surface naTuRal language GENerator - Prolog based system.

== CLINT ==
http://www.cs.bgu.ac.il/~elhadad/clint.html

CLINT is a hybrid template / word-based generation system with an example application of
business letter generation. The system is written in C++ and runs under Microsoft Windows.


== CRISP ==
[http://code.google.com/p/crisp-nlg/ CRISP] is Alexander Koller's NLG system that tries to cast both microplanning and sentence realisation as an AI planning problem. The code is a mixture of Java and Scala, a scripting language for the Java virtual machine. CRISP comes with its own implementation of GraphPlan, but it can also output plans in PDDL (“Planning Domain Definition Language”, a successor to STRIPS) for use with other AI planners. License: LGPL.

== FUF/SURGE ==
[http://www.cs.bgu.ac.il/~elhadad/research.html FUF] is available as the [ftp://ftp.cs.bgu.ac.il/pub/fuf/fuf5.3.tar.gz original Common Lisp implementation] and as a C++ port called [http://www.cs.bgu.ac.il/~elhadad/cfuf.zip CFUF] which has an embedded Scheme interpreter.

For more information, see [[#SURGE]], [[#SURGE_2.3]], [[#SURG-SP]], [[#SURG-IT]].

== GenI ==
http://trac.loria.fr/~geni

surface realiser for (Feature-Based Lexicalised) Tree Adjoining Grammar and a flat MRS-like semantics (sans top handle and underspecification). Toy example grammars provided for English and French. Largish core grammar for French is under development (contact us for details). GPL, known to work under Linux and Mac OS X (potential for making it work on Windows as well). Written in Haskell. Source code avalailable via [http://www.darcs.net darcs].

== Grammar Explorer ==
http://www.stir.ac.uk/crcl/Computational-tools/Grexplorer/grexplorer.html

provides a means of exploring large-scale systemic-functional grammars in order to see how they are
organized and what kinds of things they cover. It can be used to explore the KPML resources.
Downloadable standalone executables of the grammar explorer are available for Windows 95/98/NT.
These already include a version of the Nigel grammar of English and pre-installed examples.

== HALogen ==
http://www.isi.edu/licensed-sw/halogen/

HALogen is a general-purpose natural language generation system developed by Irene Langkilde-Geary and Kevin Knight at the USC Information Sciences Institute.
The download package consists of the symbolic generator, the forest ranker, and some sample inputs. The symbolic generator includes the Sensus Ontology dictionary (which is based on WordNet). The forest ranker includes a 250-million word ngram language model (unigram, bigram, and trigram) trained on WSJ newspaper text. The symbolic generator is written in LISP and requires a CommonLisp interpreter.


== KPML ==

http://www.purl.org/net/kpml

The KPML system offers a robust, mature platform for large-scale grammar engineering that is particularly oriented to multilingual grammar development and generation. It is particularly targetted at providing resources for realistic but broad-coverage generation applications, where both flexibility of expression and speed of generation are at issue—for example in online webpage generation or spoken dialogue. KPML is also used extensively in multilingual text generation research and for teaching. It is based on systemic functional linguistics.

The KPML system was a direct descendent of the Penman text generation system, as developed further
multilingually in cooperative work between
the Komet (http://www.darmstadt.gmd.de/publish/komet/index.html)
project in Darmstadt and the Systemic Modelling Group
at Macquarie University. Downloadable standalone executables of the system are available for
PCs running Windows. The source code is written in ANSI Common Lisp and uses the
Common Lisp Interface Manager (CLIM).
The system has been compiled and tested[
under Franz Allegro Common Lisp (4.2, 4.3, 4.3.1, 5.0, 6.0, 7.0)
for Unix and Franz Allegro Common Lisp 3.0
and Harlequin Lispworks 4.0, 4.1, 4.2 for Windows.
It is possible to use the system without the window interface as a generator serving requests for generation across sockets or via files.

A growing set of generation grammars are under development for a variety of languages, inlcluding English, Spanish, Dutch, Chinese, German, Czech, and more. See the
Generation Bank (http://www.fb10.uni-bremen.de/anglistik/langpro/kpml/genbank/generation-bank.html )
for current examples. The development of further languages and of extensions to existing resources are very welcome!

== LKB ==
[http://wiki.delph-in.net/moin/LkbTop LKB] ([[Linguistic Knowledge Builder]]) is a grammar engineering environment for unification-based formalisms, typically HPSG.
It includes a [http://wiki.delph-in.net/moin/LkbGeneration realiser] that takes as input Minimal Recursion Semantics (MRS). LKB is implemented in Common Lisp, and is freely available under an open source license.

== Multimodal Unification Grammar ==
http://www.david-reitter.com/compling/mug/

MUG Workbench is a development and debugging tool for Multimodal NLG. The grammar formalism supported is
Multimodal Functional Unification Grammar (MUG). The MUG system runs MUG grammars with fixed (test cases)
and arbitrary input specifications to produce output in a natural language, graphical user interface and
possibly in other modes. It is designed to do three things:
- Multimodal Fission (distributing output to interaction/communication modes)
- Some sentence planning (chosing information to include in the utterance)
- Natural Language and graphical user interface realization (producing some form of output)
The MUG system does these three jobs in parallel. MUG Workbench can serve to inspect the data-structures
used during generation. It should help you to learn more about the nature of unification grammars used
for parsing or natural language generation. Furthermore, the MUG Workbench is helpful in debugging your grammars.

== NaturalOWL ==
http://www.aueb.gr/users/ion/software/NaturalOWL1.1.tar.gz NaturalOWL (version 1.1)

Generates descriptions of entities and classes from OWL ontologies that have been annotated with linguistic and user modeling resources expressed in RDF. Currently supports English and Greek. Extensions for other languages welcome. NaturalOWL can also be used as a [http://protege.stanford.edu/ Protégé] plug-in. See [http://www.aueb.gr/users/ion/publications.html here] for publications describing NaturalOWL. (GPL)

==NLGen==
The [https://launchpad.net/nlgen NLGen] natural language generation system applies the [http://www.opencog.org/wiki/SegSim SegSim strategy] for generating English sentences. Probabilistic inference for sentence construction is based on a statistical analysis of [http://opencog.org/wiki/RelEx RelEx] output. Not to be confused with NLGen2, below, which uses a different sentence generation theory. See demo: [http://novamente.net/example/nlp.html Demo of AI Virtual Pet Answering Simple Questions].

== NLGen2 ==
The [https://launchpad.net/nlgen2 NLGen2] natural language generation system uses [http://opencog.org/wiki/RelEx RelEx] dependency parses, together with [http://www.abisource.com/projects/link-grammar/ Link Grammar] linkage analysis to generate English-language output. Not to be confused with NLGen, above, which uses a different sentence generation theory. Reference: Blake Lemoine, "[http://www.louisiana.edu/~bal2277/NLGen2.doc NLGen2: A Linguistically Plausible, General Purpose Natural Language Generation System]".

== OpenCCG ==
[http://openccg.sourceforge.net/ OpenCCG], the OpenNLP CCG Library (formerly Grok), is both a parser and a realizer for [[Combinatory Categorial Grammar]]. It has been used in several dialog systems. The realizer has been enhanced with n-gram models and a supertagging approach called hypertagging. OpenCCG is implemented in Java, and is freely available under the LGPL.

== Project Reporter ==
http://www.cogentex.com/products/reporter

Project Reporter generates dynamic web-based project status reports from files created with Microsoft Project or
other compatible project management software. Reports feature hyperlinked textual descriptions of
project elements, as well as coordinated multimodal display with an interactive Gantt chart applet.
Commercial product. Implemented in Java. Free 30-day evaluation; on-line demo on website.

== RAGS (Reference Architecture for Generation Systems) software ==
http://www.csd.abdn.ac.uk/~cmellish/rags/deliverables/

Deliverables from the RAGS project - RAGSOCKS software for interfacing modules using RAGS data representations,
example RAGS module (genetic algorithm based text planner) and RAGS wrapper for FUF/SURGE.

== RSTTool ==
http://www.dai.ed.ac.uk/staff/personal_pages/micko/RSTTool/

is a tool which allows you to graphically annotate the
rhetorical structure of your text. The structure can be saved in an xml format, or save
eps versions of the structure diagram for inclusion in Latex, etc. Written in Tcl/Tk.
Runs on any machine.

== Simplenlg ==

http://www.csd.abdn.ac.uk/~ereiter/simplenlg

is an ultra-simple Java-based realiser. Its
grammatical coverage and syntactic knowledge is
minuscule compared to KPML or FUF/SURGE.
However, because it is so simple, its relatively
easy for people to learn how to use it. It has
been used by many people in Aberdeen, and also
for teaching. It is set up as a Java package,
so it can only be used by Java programs.

== SPUD ==
[http://www.cs.rutgers.edu/~mdstone/nlg.html SPUD] (Sentence Planner Using Descriptions) is Matthew Purver's LTAG-based NLG system. There are two versions: SPUD version 0.01 was written in SML. Later versions, known as SPUD lite, are written in Prolog. The small codebase of SPUD lite makes it ideal for teaching, but it is also used in dialog system prototypes.

== Suregen-2 ==
[http://www.suregen.de/00023.html Suregen] is “a hybrid, ontology based and NLG-oriented formalism for generating text for documents in clinical medicine.”
The system Suregen-2 is written in (Allegro) Common Lisp. A [http://www.suregen.de/ftp/standalone1.zip demo system] which runs under Windows is available for download. A [http://www.suregen.de/ftp/selfrunningdemo.zip screencast video] shows data being entered into computer forms using mouse and keyboard while a feedback text is continually updated and shown below. (Try playing the AVI file in [http://www.videolan.org/vlc/ VLC] if you run into problems.) Perhaps this system could be considered an instance of the [http://en.wikipedia.org/wiki/WYSIWYM_(Meant) WYSIWYM] approach.

== SURGE ==
http://www.cs.bgu.ac.il/surge/

Syntactic realization package. (A CommonLisp package providing an interpreter for a functional
unification formalism called FUF and SURGE, a large grammar of English written in FUF.) Offers download of SURGE 2.2.

== SURGE 2.3 ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The latest version of Surge, including support for written dialogue, and expanded
syntactic coverage based on the Penn TreeBank.

== SURG-SP ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

Systemic Unification Reusable Grammar for Spanish is a large scale
Spanish grammar allowing systems which already use FUF/SURGE for English NLG to be able
to generate syntactically (and many times semantically) equivalent text in Spanish when
new lexical items are introduced. SURG-SP makes use of inputs almost identical to the
English version Surge 2.3.

== SURG-IT ==
http://homepages.inf.ed.ac.uk/ccallawa/resources.html

The Italian version of Surge 2.3.

== TG/2 ==
http://www.dfki.de/pas/f2w.cgi?lts/tg2-e

is a shallow verbalizer that can be quickly accustomed to new domains and tasks.
It combines context-free grammars with templates and canned
text in a single formalism. Thus the granularity of the language model may depend on the application
needs. The system currently runs under Solaris 2.5. It is available freely under a research license.

[[Category:Software]]
{{SIGGEN Wiki}}

Morphology software for English

2008-11-13T00:53:06Z

Linas: /* Morphology */ MAP appears to be free, too

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French -- perl scripts, GPL license
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

[[Category:Morphology]]
[[Category:Software]]

Morphology software for English

2008-11-13T00:51:12Z

Linas: /* Morphology */ flemm is actually GPL not proprietary

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French -- perl scripts, GPL license
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

[[Category:Morphology]]
[[Category:Software]]

Morphology software for English

2008-11-13T00:50:03Z

Linas: revert my last two edits; its actually handy to have all langauges on one page.

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

[[Category:Morphology]]
[[Category:Software]]

Morphology software for English

2008-11-13T00:48:17Z

Linas: /* Proprietary software */ Move Flemm to Resources for French -- it is GPL license, btw, not proprietrary

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms

*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

[[Category:Morphology]]
[[Category:Software]]

Resources for French

2008-11-13T00:47:22Z

Linas: Flemm 3.1 -- move from english page.

==Corpora==

* [http://atilf.atilf.fr/dmf.htm Base Textuelle de Moyen Francais]
* [http://corpora.informatik.uni-leipzig.de/ French plain text and Co-occurrences at LCC]
* [http://www.up.univ-mrs.fr/veronis/donnees/index.html French Stopword List]
* [http://www.cnrtl.fr/lexiques/morphalou/ Lexique Morphalou]
* [http://w3.univ-tlse2.fr/erss/verbaction/main.html Lexique Verbaction]

==Morphology==
* [http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French --free, GPL license.

[[Category:Resources by language|French]]

Morphology software for English

2008-11-13T00:42:58Z

Linas: /* Free software */ move the Morph It link to the Resources for Italian page

'''[[Software]] - Morphology and part of speech tagging'''

For languages other than English, see [[List of resources by language]].

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism
*[http://www.fsmbook.com Xerox/PARC] - finite-state morphological analysis/generation using xfst, lexc, twolc

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==

===Free software===


*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

===Proprietary software===



*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging

[[Category:Morphology]]
[[Category:Software]]

Resources for Italian

2008-11-13T00:40:15Z

Linas: /* Morphology */ whoops -- h3 not h2

== Tools for Italian ==

=== Tokenisers ===
* [http://tcc.itc.it/projects/textpro/index.php TextPro]

=== POS taggers ===
* [http://tcc.itc.it/projects/textpro/index.php TextPro]
* [http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html TreeTagger]

===Morphology===
* [http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.47] - a free morphological resource for the Italian language

=== Named Entity Recognisers ===
* [http://tcc.itc.it/projects/ontotext/entitypro.html EntityPro]

=== Temporal Expressions ===
* [http://tcc.itc.it/projects/ontotext/ita-chronos.html ITA-Chronos]

=== Parsers ===
* [http://ai-nlp.info.uniroma2.it/external/chaosproject/ Chaos] - Robust syntactic parser for Italian and for English

=== Generators ===
* [http://tcc.itc.it/projects/xig/index.html XIG] - Interchange to Italian Generator

== Resources for Italian ==

=== Corpora ===


* [http://www.istc.cnr.it/material/database/colfis/ ColFIS Corpus e Lessico di Frequenza dell'Italiano Scritto]
* [http://corpus.cilta.unibo.it:8080/coris_ita.html Corpus di Italiano Scritto contemporaneo (CORIS/CODIS)]
* [http://corpora.informatik.uni-leipzig.de/ Italian plain text and Co-occurrences at LCC]
* [http://languageserver.uni-graz.at/badip/badip/20_corpusLip.php LIP - Lessico di frequenza dell'Italiano Parlato - Access via BADIP]
* [http://multisemcor.itc.it/ MultiSemCor] - English/Italian parallel corpus
* [http://www.uni-duisburg.de/Fak2/FremdPhil/Romanistik/Personal/Burr/humcomp/ Oxford Text Archive Corpus of Italian Newspapers]
* [http://tlio.ovi.cnr.it/TLIO/ Tesoro della lingua italiana delle origini (TLIO)]

=== Tagsets ===
* [http://tcc.itc.it/projects/textpro/index.php LemmaPro] - Italian POS tagset for LemmaPro

=== Treebanks ===
* [http://catalog.elra.info/retd/product_info.phpproducts_id=879&osCsid=0cef41a96779ef79b67c71bbf35e6eaa ISST] - Italian Syntactic-Semantic Treebank
* [http://www.di.unito.it/~tutreeb/ TUT] - Turin University Treebank
* [http://157.138.41.87/HTMLipar/indexparsing_a.htm VIT] - Venice Italian Treebank

=== WordNets ===
* [http://www.elda.fr/ EuroWordNet]
* [http://multiwordnet.itc.it/english/home.php MultiWordNet] - a multilingual lexical database in which the Italian WordNet is strictly aligned with Princeton WordNet 1.6

=== Lexicons ===
* [http://www.ilc.cnr.it/clips/PSC_decription.htm PAROLE-SIMPLE-CLIPS] - a four-layered, general purpose computational lexicon

== Links ==
* [http://evalita.itc.it/ Evalita] - Evaluation of NLP tools for Italian

[[Category:Resources by language|Italian]]

Resources for Italian

2008-11-13T00:39:44Z

Linas: /* Tools for Italian */ copy morphology entry from the english page

== Tools for Italian ==

=== Tokenisers ===
* [http://tcc.itc.it/projects/textpro/index.php TextPro]

=== POS taggers ===
* [http://tcc.itc.it/projects/textpro/index.php TextPro]
* [http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html TreeTagger]

==Morphology==
* [http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.47] - a free morphological resource for the Italian language

=== Named Entity Recognisers ===
* [http://tcc.itc.it/projects/ontotext/entitypro.html EntityPro]

=== Temporal Expressions ===
* [http://tcc.itc.it/projects/ontotext/ita-chronos.html ITA-Chronos]

=== Parsers ===
* [http://ai-nlp.info.uniroma2.it/external/chaosproject/ Chaos] - Robust syntactic parser for Italian and for English

=== Generators ===
* [http://tcc.itc.it/projects/xig/index.html XIG] - Interchange to Italian Generator

== Resources for Italian ==

=== Corpora ===


* [http://www.istc.cnr.it/material/database/colfis/ ColFIS Corpus e Lessico di Frequenza dell'Italiano Scritto]
* [http://corpus.cilta.unibo.it:8080/coris_ita.html Corpus di Italiano Scritto contemporaneo (CORIS/CODIS)]
* [http://corpora.informatik.uni-leipzig.de/ Italian plain text and Co-occurrences at LCC]
* [http://languageserver.uni-graz.at/badip/badip/20_corpusLip.php LIP - Lessico di frequenza dell'Italiano Parlato - Access via BADIP]
* [http://multisemcor.itc.it/ MultiSemCor] - English/Italian parallel corpus
* [http://www.uni-duisburg.de/Fak2/FremdPhil/Romanistik/Personal/Burr/humcomp/ Oxford Text Archive Corpus of Italian Newspapers]
* [http://tlio.ovi.cnr.it/TLIO/ Tesoro della lingua italiana delle origini (TLIO)]

=== Tagsets ===
* [http://tcc.itc.it/projects/textpro/index.php LemmaPro] - Italian POS tagset for LemmaPro

=== Treebanks ===
* [http://catalog.elra.info/retd/product_info.phpproducts_id=879&osCsid=0cef41a96779ef79b67c71bbf35e6eaa ISST] - Italian Syntactic-Semantic Treebank
* [http://www.di.unito.it/~tutreeb/ TUT] - Turin University Treebank
* [http://157.138.41.87/HTMLipar/indexparsing_a.htm VIT] - Venice Italian Treebank

=== WordNets ===
* [http://www.elda.fr/ EuroWordNet]
* [http://multiwordnet.itc.it/english/home.php MultiWordNet] - a multilingual lexical database in which the Italian WordNet is strictly aligned with Princeton WordNet 1.6

=== Lexicons ===
* [http://www.ilc.cnr.it/clips/PSC_decription.htm PAROLE-SIMPLE-CLIPS] - a four-layered, general purpose computational lexicon

== Links ==
* [http://evalita.itc.it/ Evalita] - Evaluation of NLP tools for Italian

[[Category:Resources by language|Italian]]

Resources for Persian

2008-11-13T00:13:26Z

Linas: add biblio entry

==Machine translation systems==

===Free software===

===Proprietary===
*[http://crl.nmsu.edu/Research/Projects/shiraz/index.html The Shiraz project] (Persian -> English)

==Morphology tools==
===Free software===
*[http://sourceforge.net/projects/perstem Perstem] - Persian stemmer, light morphological analyzer, and character set converter.
*[http://apertium.svn.sourceforge.net/svnroot/apertium/trunk/apertium-tg-fa/apertium-tg-fa.fa.dix.xml Morphological dictionary] — compiled using [http://xixona.dlsi.ua.es/wiki/index.php/lttoolbox lttoolbox].

== Corpora ==


*[http://ece.ut.ac.ir/DBRG/Bijankhan/ Bijankhan corpus]
*[http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC96S50 CALLFRIEND Farsi (speech)]
*[http://ece.ut.ac.ir/dbrg/hamshahri/ Hamshahri corpus]
*[http://www.elda.org/catalogue/en/speech/S0112.html Persian speech database Farsdat]

==Parser==
===Free software===
* [http://www.ling.ohio-state.edu/~jonsafari/persianlg/ Persian dictionaries], by [http://www.ling.ohio-state.edu/~jonsafari/ Jon Dehdari], for the [http://www.abisource.com/projects/link-grammar/ Link-Grammar parser]. These require the Perstem stemming package, above.

==Bibliography==
* Dehdari, Jon, and Deryle Lonsdale. 2008. [http://www.ling.ohio-state.edu/~jonsafari/papers/dehdari_lonsdale_2005.pdf A link grammar parser for Persian]. In Karimi, S., Samiian, V., and Stilo, D., editors, ''Aspects of Iranian Linguistics'', volume 1. Cambridge Scholars Press. ISBN: 978-18-471-8639-3 ([http://www.ling.ohio-state.edu/~jonsafari/bib/dehdarilonsdale2005.bib.txt BIB])

* Feili, H. and G. Ghassem-Sani (2004) "An Application of Lexicalized Grammars in English-Persian Translation". ''Proceedings of the 16th European Conference on Artificial Intelligence (ECAI 2004)'', 24-27 Aug. 2004, Universidad Politecnica de Valencia, Valencia, Spain, pp. 596-600. [http://sharif.edu/~sani/papers/Feili_SaniE2.pdf PDF]
* Megerdoomian, K. (2000) "Unification-Based Persian Morphology". ''Proceedings of CICLing 2000'', Alexander Gelbukh, Center of Investigation on Computation-IPN, Mexico, 2000. [http://crl.nmsu.edu/Research/Projects/shiraz/publications/papers/Cicling.pdf PDF]
* Megerdoomian, K. (2004) "Finite-State Morphological Analysis of Persian". ''COLING 2004 Computational Approaches to Arabic Script-based Languages''. Ali Farghaly and Karine Megerdoomian editors, Geneva, Switzerland, 2004, pgs. 35-41. [http://acl.ldc.upenn.edu/coling2004/W5/pdf/W5-7.pdf PDF]

==See also==
*[[Resources for Tajik]]

==External links==
*[http://home.byu.net/jmd56/index.html the Jon safari] (link parser, small lexicon, stemmer, morphological analysis tools)

[[Category:Resources by language|Persian]]

Resources for Arabic

2008-11-13T00:06:40Z

Linas: add section header

==Morphology==

===Free software===
*[https://sourceforge.net/projects/aramorph/ AraMorph - Perl] - An Arabic morphological analyzer and part-of-speech tagger written in Perl (originally by Tim Buckwalter)
*[http://www.nongnu.org/aramorph/ AraMorph - Java] - An Arabic morphological analyzer and part-of-speech tagger rewritten in Java for [http://lucene.apache.org/ Lucene]

===Proprietary===
*[http://www.arabic-morphology.com Xerox Arabic Morphological Analyzer and Generator]

==Corpora==
*[http://www.ldc.upenn.edu/Catalog/LDC2001T55.html Arabic Newswire Part 1]

==Parser==
===Free software===
* [http://www.ling.ohio-state.edu/~jonsafari/arabiclg/arabiclg.20060829.tar.bz2 Arabic dictionaries], by [http://www.ling.ohio-state.edu/~jonsafari/ Jon Dehdari], for the [http://www.abisource.com/projects/link-grammar/ Link-Grammar parser]. These require the Aramorph stemming package, above.

==Bibliography==

==External links==
*[http://www.elsnet.org/acl2001-arabic.html ACL/EACL 2001 Workshop on Arabic NLP]
*[http://www1.cs.columbia.edu/~mdiab/software/ASVMTools_2.0.tar.gz Basic Arabic Processing Tools]
*[http://acl.ldc.upenn.edu/coling2004/W5/index.html COLING 2004 Workshop on computational approaches to Arabic script-based languages]

[[Category:Resources by language|Arabic]]

Resources for Arabic

2008-11-13T00:04:39Z

Linas: Arabic dicttionaries for the link-grammar parser

==Morphology==

===Free software===
*[https://sourceforge.net/projects/aramorph/ AraMorph - Perl] - An Arabic morphological analyzer and part-of-speech tagger written in Perl (originally by Tim Buckwalter)
*[http://www.nongnu.org/aramorph/ AraMorph - Java] - An Arabic morphological analyzer and part-of-speech tagger rewritten in Java for [http://lucene.apache.org/ Lucene]

===Proprietary===
*[http://www.arabic-morphology.com Xerox Arabic Morphological Analyzer and Generator]

==Corpora==
*[http://www.ldc.upenn.edu/Catalog/LDC2001T55.html Arabic Newswire Part 1]

==Parser==
* [http://www.ling.ohio-state.edu/~jonsafari/arabiclg/arabiclg.20060829.tar.bz2 Arabic dictionaries], by [http://www.ling.ohio-state.edu/~jonsafari/ Jon Dehdari], for the [http://www.abisource.com/projects/link-grammar/ Link-Grammar parser]. These require the Aramorph stemming package, above.

==Bibliography==

==External links==
*[http://www.elsnet.org/acl2001-arabic.html ACL/EACL 2001 Workshop on Arabic NLP]
*[http://www1.cs.columbia.edu/~mdiab/software/ASVMTools_2.0.tar.gz Basic Arabic Processing Tools]
*[http://acl.ldc.upenn.edu/coling2004/W5/index.html COLING 2004 Workshop on computational approaches to Arabic script-based languages]

[[Category:Resources by language|Arabic]]

Parsing (State of the art)

2008-04-22T18:20:20Z

Linas: /* References */ add a ref

* '''Performance measure:''' PARSEVAL - the [http://nlp.cs.nyu.edu/evalb/ evalb] program
* '''Training data:''' sections 2-22 of Wall Street Journal corpus
* '''Testing data:''' section 23 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results (PARSEVAL)
! Comments
|-
| Johnson & Charniak's Parser
| Lexicalized N-Best PCFG + Discriminative re-reanking
| Johnson and Charniak (2005)
| [http://www.cog.brown.edu/~mj/Software.htm download]
| 91.4%
| works well also on Brown
|-
| Collins' Parser
| Lexicalized PCFG
| Collins (1999), Bikel (2004)
| [http://www.cis.upenn.edu/~dbikel/software.html Dan Bikel's implementation]
| ?
| ?
|-
| Berkeley Parser
| Automatically induced PCFG
| Petrov et al. (2006), Petrov and Klein (2007)
| [http://nlp.cs.berkeley.edu/Main.html#Parsing Berkeley Parser]
| 90.1%
| works well also for Chinese and German
|-
| Link Grammar
| Dependency grammar
| Temperley, Sleator, Lafferty, others (1995-2006)
| [http://www.abisource.com/projects/link-grammar/ Actively supported project]
| ?
| Persian, Arabic, Chinese, German, Russian dictionaries have been developed.
|-
|}

== References ==

Bikel, D. (2004). ''[http://www.cis.upenn.edu/~dbikel/papers/thesis.pdf On The Parameter Space of Generative Lexicalized Statistical Parsing Models]''. PhD Thesis, Computer and Information Science, University of Pennsylvania.

Collins, M. (1999). ''[http://people.csail.mit.edu/mcollins/papers/thesis.ps Head-driven Statistical Models for Natural Language Parsing]''. PhD Thesis, Computer and Information Science, University of Pennsylvania.

Johnson, M., and Charniak, E. (2005). [http://acl.ldc.upenn.edu/P/P05/P05-1022.pdf Coarse-to-fine n-best parsing and MaxEnt discriminative reranking]. ''Proceedings of the 43rd Annual Meeting of the ACL'', pages 173–180, Ann Arbor, June 2005.

Petrov, S., Barrett, L., Thibaux, R., and Klein, D. (2006). [http://www.eecs.berkeley.edu/~petrov/data/acl06.pdf Learning accurate, compact, and interpretable tree annotation]. ''Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL'', pages 433–440, Sydney.

Petrov, S., and Klein, D. (2007). [http://www.eecs.berkeley.edu/~petrov/data/naacl07.pdf Improved inference for unlexicalized parsing]. ''Proceedings of NAACL 2007'', pages 404-411.

Sleator, Daniel & Davy Temperly (1993) "[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/link/pub/www/papers/ps/LG-IWPT93.pdf Parsing English with a Link Grammar]", ''Third International Workshop on Parsing Technologies''.

== See also ==

* [[State of the art]]

== External links ==

* PARSEVAL - the [http://nlp.cs.nyu.edu/evalb/ evalb] program

[[Category:State of the art]]

Parsing (State of the art)

2008-04-22T18:12:21Z

Linas: /* Table of results */ link grammar

* '''Performance measure:''' PARSEVAL - the [http://nlp.cs.nyu.edu/evalb/ evalb] program
* '''Training data:''' sections 2-22 of Wall Street Journal corpus
* '''Testing data:''' section 23 of Wall Street Journal corpus

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! System name
! Short description
! Main publications
! Software
! Results (PARSEVAL)
! Comments
|-
| Johnson & Charniak's Parser
| Lexicalized N-Best PCFG + Discriminative re-reanking
| Johnson and Charniak (2005)
| [http://www.cog.brown.edu/~mj/Software.htm download]
| 91.4%
| works well also on Brown
|-
| Collins' Parser
| Lexicalized PCFG
| Collins (1999), Bikel (2004)
| [http://www.cis.upenn.edu/~dbikel/software.html Dan Bikel's implementation]
| ?
| ?
|-
| Berkeley Parser
| Automatically induced PCFG
| Petrov et al. (2006), Petrov and Klein (2007)
| [http://nlp.cs.berkeley.edu/Main.html#Parsing Berkeley Parser]
| 90.1%
| works well also for Chinese and German
|-
| Link Grammar
| Dependency grammar
| Temperley, Sleator, Lafferty, others (1995-2006)
| [http://www.abisource.com/projects/link-grammar/ Actively supported project]
| ?
| Persian, Arabic, Chinese, German, Russian dictionaries have been developed.
|-
|}

== References ==

Bikel, D. (2004). ''[http://www.cis.upenn.edu/~dbikel/papers/thesis.pdf On The Parameter Space of Generative Lexicalized Statistical Parsing Models]''. PhD Thesis, Computer and Information Science, University of Pennsylvania.

Collins, M. (1999). ''[http://people.csail.mit.edu/mcollins/papers/thesis.ps Head-driven Statistical Models for Natural Language Parsing]''. PhD Thesis, Computer and Information Science, University of Pennsylvania.

Johnson, M., and Charniak, E. (2005). [http://acl.ldc.upenn.edu/P/P05/P05-1022.pdf Coarse-to-fine n-best parsing and MaxEnt discriminative reranking]. ''Proceedings of the 43rd Annual Meeting of the ACL'', pages 173–180, Ann Arbor, June 2005.

Petrov, S., Barrett, L., Thibaux, R., and Klein, D. (2006). [http://www.eecs.berkeley.edu/~petrov/data/acl06.pdf Learning accurate, compact, and interpretable tree annotation]. ''Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL'', pages 433–440, Sydney.

Petrov, S., and Klein, D. (2007). [http://www.eecs.berkeley.edu/~petrov/data/naacl07.pdf Improved inference for unlexicalized parsing]. ''Proceedings of NAACL 2007'', pages 404-411.

== See also ==

* [[State of the art]]

== External links ==

* PARSEVAL - the [http://nlp.cs.nyu.edu/evalb/ evalb] program

[[Category:State of the art]]

Morphology software for English

2008-04-22T18:02:28Z

Linas: /* Free software */ more about relex

'''[[Software]] - Morphology and part of speech tagging'''

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides English-language part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Also provides resulting stems. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==


*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging
*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

[[Category:Morphology]]
[[Category:Software]]

Morphology software for English

2008-04-22T18:00:01Z

Linas: /* Free software */ Relex

'''[[Software]] - Morphology and part of speech tagging'''

== Morphology ==

===Free software===


*[http://clipdemos.umiacs.umd.edu/catvar/ Catvar 2.0] - The Categorial Variation Database for English (OSL)
*[http://wiki.apertium.org/wiki/lttoolbox lttoolbox] -- lexical processing tools for building morphological analysers/generators with XML specification files (GPL)
*[http://sslmitdev-online.sslmit.unibo.it/linguistics/morph-it.php Morph-It! version 0.31] - a free morphological resource for the Italian language
*[http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html SFST] - Stuttgart Finite State Transducer Tools (GPL)

===Proprietary software===


*[http://www.ru.nl/celex/ CELEX database] - Dutch, English, and German word forms
*[http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Flemmv3.1] - inflectional morphology parser for French
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/fonol/0.html FONOL] - Phonological Programming Language (non-commercial only)
*[http://services.canoo.com/MorphologyBrowser.html German Morphology Browser]
*[http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html Hebrew Morphological Parser]
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/map/0.html MAP] - Cambridge/Edinburgh Morphological Analyzer and Dictionary System (freeware)
*[http://bach.arts.kuleuven.ac.be/~piet/morlex/index.html MORLEX] - A lexical database for French
*[http://www.informatics.susx.ac.uk/research/nlp/carroll/morph.html morpha and morphg] - fast and robust morphological analysis and generation for English, from John A. Carroll (non-commercial only)
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/morfogen/0.html MORFOGEN] - a Morphology Grammar Builder and Dictionary Interface Tool
*[http://nlp.cs.nyu.edu/nomlex/index.html NOMLEX] - a dictionary of English nominalizations
*[http://www.sil.org/pckimmo/about_pc-kimmo.html PC-KIMMO] - a Two-level Processor for Morphological Analysis, including KGEN, KTEXT, and Englex
*[http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/nlp/morph/tulip/0.html TULIP] - a two level phonological formalism

==Part of speech tagging==

===Free software===

*[http://acopost.sourceforge.net/ ACOPOST - A Collection Of PoS Taggers] Maximum Entropy Tagger, Trigram Tagger, Transformation-based Tagger, Example-based tagger
*[http://wiki.apertium.org/wiki/Tagger_training Tagger training] on the Apertium Wiki (HMM + constraint based)
*[http://nltk.sourceforge.net/ NLTK - Natural Language Toolkit] Regexp Tagger, N-Gram Tagger, Brill Tagger, HMM Tagger, plus a freely downloadable book with a chapter on tagging
*[http://opencog.org/wiki/RelEx RelEx] - provides part-of-speech tagging, entity tagging, as well as other types of tags (gender, date, money ...), after performing a deep parse, so that tags agree with parse. Apache 2.0 License.
*[http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous rule-based morphosyntactic disambiguation and partial parsing
* [http://beta.visl.sdu.dk/cg3.html VISL Constraint Grammar] rule based disambiguation (GPL)

===Proprietary software===


==Combined morphology and tagging==


*[http://nlp.postech.ac.kr/DownLoad/k_api.html Korean morphological analyzer and part-of-speech tagger]
*[http://www.nlplab.cn/resource/CIP/neucsp.zip NEUCSP] - a tool for Chinese Word Segmentation and POS tagging
*[http://www.cis.upenn.edu/~xtag/swrelease.html XTAG] - tools for parsing and grammar development, including morphological analysis and tagging, as described in [http://www.cs.mu.oz.au/acl/C/C94/C94-2149.pdf XTAG System - A Wide Coverage Grammar for English] and [http://arxiv.org/abs/cmp-lg/9410024 A Freely Available Wide Coverage Morphological Analyzer for English]

[[Category:Morphology]]
[[Category:Software]]

Natural language generation software

2008-04-18T19:36:34Z

Linas: replace KPML with latest URL

'''[[Software]] - Natural language generation'''


*[http://www.isi.edu/licensed-sw/halogen/index.html HALogen Natural Language Generation system]
*[http://kwicfinder.com/kfNgram/kfNgramHelp.html kfNgram]
*[http://www.fb10.uni-bremen.de/anglistik/langpro/kpml/README.html KPML]
*[http://www.aueb.gr/users/ion/software/NaturalOWL.tar.gz NaturalOWL] Generates descriptions of individuals and classes from OWL ontologies that have been annotated with linguistic and user modeling resources expressed in RDF. Currently supports English and Greek. Extensions for other languages welcome. NaturalOWL can also be used as a [http://protege.stanford.edu/ Protégé] plug-in. See [http://www.aueb.gr/users/ion/publications.html here] for publications describing NaturalOWL. (GPL)

[[Category:Software]]

User:Linas

2008-04-18T19:12:45Z

Linas: basics

My name is [http://www.linas.org Linas Vepštas]. I am best contacted at [http://en.wikipedia.org/wiki/User:Linas my wikipedia user page].

Semantics software for English

2008-04-18T19:05:27Z

Linas: Add relex

'''[[Software]] - Semantics'''


*[http://svn.ask.it.usyd.edu.au/trac/candc/wiki Boxer] - wide-coverage semantics based on DRT (Discourse Representation Theory)
*[http://www.connexor.com/software/semantics/ Connexor Machinese Semantics]
*[http://sws.clearforest.com/blog ClearForest Semantic Web Service (API) ]
*[http://www.intellexer.com/ Intellexer - Natural Language Searching Technologies]
*[http://www.ling.upenn.edu/lambda Lambda Calculator] - pedagogical software for lambda calculus and formal semantics in the style of the Heim & Kratzer (1998) textbook
*[http://nltk.org NLTK semantics] - Python libraries for lambda calculus, first order model checking, DRT, glue semantics, a tableau theorem prover and interfaces to external inference programs (Prover9, Mace4)
*[http://opencog.org/wiki/RelEx RelEx], an English-language semantic relationship extractor. Provides framing/grounding also, as well as tagging of various sorts. Open source, Java, Apache license.
*[http://senseclusters.sourceforge.net/ SenseClusters]
*[http://www.comp.lancs.ac.uk/ucrel/usas/ UCREL] - Semantic Analysis System
*[http://www.coli.uni-saarland.de/projects/chorus/utool/ utool] The Swiss Army Knife of Underspecification

[[Category:Semantics]]
[[Category:Software]]

Parsers for English

2008-04-18T18:58:53Z

Linas: update info for link grammar

* [http://www.connexor.com/software/syntax/ Connexor Machinese Syntax and parser]
* [http://svn.ask.it.usyd.edu.au/trac/candc C&C parser for Combinatory Categorial Grammar]
* [http://www.delph-in.net/ DELPH-IN], Deep Linguistic Processing with HPSG (Head-Driven Phrase Structure Grammar)
* [http://www.link.cs.cmu.edu/link/ Link Grammar Parser -- a dependency parser] from CMU. The latest, supported versions are hosted [http://www.abisource.com/projects/link-grammar/ here], at Abiword. Open source, BSD license.
* [[Minipar]]
* [http://openccg.sf.net OpenCCG parser and grammar development environment for Combinatory Categorial Grammar]
* [http://www.coli.uni-saarland.de/projects/salsa/shal/ Shalmaneser]
* [http://nlp.ipipan.waw.pl/Spejd/ Spejd - Shallow Parsing and Disambiguation Engine] a GPL tool for simultaneous partial parsing and rule-based morphosyntactic disambiguation
* [http://www.ling.helsinki.fi/~tapanain/dg/ Syntactic dependency parser for English]


==Non-English Parsers==

*[http://bach.arts.kuleuven.ac.be/~piet/vertex/index.html VERTEX - A chart parser for unification grammars (French)]


[[Category:Parsers|*]]