https://aclweb.org/aclwiki/api.php?action=feedcontributions&user=Auser&feedformat=atomACL Wiki - User contributions [en]2024-03-28T14:03:52ZUser contributionsMediaWiki 1.35.2https://aclweb.org/aclwiki/index.php?title=POS_Induction_(State_of_the_art)&diff=8631POS Induction (State of the art)2011-01-27T22:07:19Z<p>Auser: evaluate 45 labels</p>
<hr />
<div>==Evaluation==<br />
'''Many-to-1:''' Map every induced label to a gold standard tag greedily (45 labels to 45 tags of the Penn tag set). Use the mapping to compute tag accuracy on the Wall Street Journal portion of the Penn TreeBank. <br />
<br />
==Results==<br />
<br />
{| border="1" cellpadding="5" cellspacing="1" width="100%"<br />
|-<br />
! System name<br />
! Short description<br />
! Main publications<br />
! Software<br />
! Many-to-1<br />
|-<br />
| Brown+proto<br />
| MRF initialized with Brown prototypes<br />
| Christodoulopoulos, Goldwater and Steedman (2010)<br />
| <br />
| 76.1%<br />
|-<br />
| <br />
| Logistic regression with features and LBFGS<br />
| Berg-Kirkpatrick et al. (2010)<br />
| <br />
| 75.5%<br />
|-<br />
| Clark DMF<br />
| Distributional clustering + morphology + frequency<br />
| Clark (2003)<br />
| [http://www.cs.rhul.ac.uk/home/alexc/pos2.tar.gz alexc]<br />
| 71.2%*<br />
|-<br />
|}<br />
<br />
<nowiki>*</nowiki> according to Christodoulopoulos, Goldwater and Steedman (2010)<br />
<br />
== References ==<br />
<br />
* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]<br />
<br />
* [http://www.aclweb.org/anthology/N/N10/N10-1083.pdf Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010. Painless Unsupervised Learning with Features. NAACL 2010.]<br />
<br />
* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]<br />
<br />
== See also ==<br />
* [[POS Tagging (State of the art)]]<br />
* [[Part-of-speech tagging]]<br />
* [[State of the art]]<br />
<br />
<br />
[[Category:State of the art]]</div>Auserhttps://aclweb.org/aclwiki/index.php?title=POS_Induction_(State_of_the_art)&diff=8630POS Induction (State of the art)2011-01-27T21:43:15Z<p>Auser: Alexander Clark. 2003</p>
<hr />
<div>==Evaluation==<br />
'''Many-to-1:''' Mapping every induced label to a gold standard tag greedily. Use the mapping to compute tag accuracy on the Wall Street Journal part of the Penn TreeBank.<br />
<br />
==Results==<br />
<br />
{| border="1" cellpadding="5" cellspacing="1" width="100%"<br />
|-<br />
! System name<br />
! Short description<br />
! Main publications<br />
! Software<br />
! Many-to-1<br />
|-<br />
| Brown+proto<br />
| MRF initialized with Brown prototypes<br />
| Christodoulopoulos, Goldwater and Steedman (2010)<br />
| <br />
| 76.1%<br />
|-<br />
| <br />
| Logistic regression with features and LBFGS<br />
| Berg-Kirkpatrick et al. (2010)<br />
| <br />
| 75.5%<br />
|-<br />
| Clark DMF<br />
| Distributional clustering + morphology + frequency<br />
| Clark (2003)<br />
| [http://www.cs.rhul.ac.uk/home/alexc/pos2.tar.gz alexc]<br />
| 71.2%*<br />
|-<br />
|}<br />
<br />
<nowiki>*</nowiki> according to Christodoulopoulos, Goldwater and Steedman (2010)<br />
<br />
== References ==<br />
<br />
* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]<br />
<br />
* [http://www.aclweb.org/anthology/N/N10/N10-1083.pdf Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010. Painless Unsupervised Learning with Features. NAACL 2010.]<br />
<br />
* [http://www.aclweb.org/anthology/E/E03/E03-1009.pdf Alexander Clark. 2003. Combining distributional and morphological information for part of speech induction. In Proceedings of EACL 2003, pages 59–66, Morristown, NJ, USA.]<br />
<br />
== See also ==<br />
* [[POS Tagging (State of the art)]]<br />
* [[Part-of-speech tagging]]<br />
* [[State of the art]]<br />
<br />
<br />
[[Category:State of the art]]</div>Auserhttps://aclweb.org/aclwiki/index.php?title=POS_Induction_(State_of_the_art)&diff=8629POS Induction (State of the art)2011-01-27T21:03:25Z<p>Auser: Berg-Kirkpatrick et al. (2010)</p>
<hr />
<div>{| border="1" cellpadding="5" cellspacing="1" width="100%"<br />
|-<br />
! System name<br />
! Short description<br />
! Main publications<br />
! Software<br />
! Many-to-1<br />
|-<br />
| Prototype-based+Brown<br />
| MRF initialized with Brown prototypes<br />
| Christodoulopoulos, Goldwater and Steedman (2010)<br />
| <br />
| 76.1%<br />
|-<br />
| <br />
| Logistic regression with features and LBFGS<br />
| Berg-Kirkpatrick et al. (2010)<br />
| <br />
| 75.5%<br />
|-<br />
|}<br />
<br />
<br />
== References ==<br />
<br />
* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010.]<br />
<br />
* [http://www.aclweb.org/anthology/N/N10/N10-1083.pdf Taylor Berg-Kirkpatrick, Alexandre Bouchard-Cote, John DeNero, and Dan Klein. 2010. Painless Unsupervised Learning with Features. NAACL 2010.]<br />
<br />
== See also ==<br />
* [[POS Tagging (State of the art)]]<br />
* [[Part-of-speech tagging]]<br />
* [[State of the art]]<br />
<br />
<br />
[[Category:State of the art]]</div>Auserhttps://aclweb.org/aclwiki/index.php?title=POS_Induction_(State_of_the_art)&diff=8626POS Induction (State of the art)2011-01-27T19:05:18Z<p>Auser: Christodoulopoulos et al , the current state-of-the-art</p>
<hr />
<div>{| border="1" cellpadding="5" cellspacing="1" width="100%"<br />
|-<br />
! System name<br />
! Short description<br />
! Main publications<br />
! Software<br />
! Many-to-1<br />
|-<br />
| Prototype-based+Brown<br />
| MRF initialized with Brown prototypes<br />
| Christodoulopoulos, Goldwater and Steedman (2010)<br />
| <br />
| 76.1%<br />
|-<br />
|}<br />
<br />
<br />
== References ==<br />
<br />
* [http://www.aclweb.org/anthology/D/D10/D10-1056.pdf Christos Christodoulopoulos, Sharon Goldwater and Mark Steedman. 2010. Two Decades of Unsupervised POS induction: How far have we come? In Proceedings of EMNLP 2010]</div>Auserhttps://aclweb.org/aclwiki/index.php?title=State_of_the_art&diff=8625State of the art2011-01-27T18:51:19Z<p>Auser: POS Induction</p>
<hr />
<div>The purpose of this section of the ACL wiki is to be a repository of ''k''-best state-of-the-art results (i.e., methods and software) for various core natural language processing tasks. <br />
<br />
As a side effect, this should hopefully evolve into a knowledge base of standard evaluation methods and datasets for various tasks, as well as encourage more effort into reproducibility of results. This will help newcomers to a field appreciate what has been done so far and what the main tasks are, and will help keep active researchers informed on fields other than their specific research. The next time you need a system for PP attachment, or wonder what is the current state of word sense disambiguation, this will be the place to visit. <br />
<br />
Please contribute! (This is also a good place for you to display your results!)<br />
<br />
<!-- Please keep this list in alphabetical order --><br />
* [[Anaphora Resolution (State of the art)|Anaphora Resolution]] (stub)<br />
* [[Attributional and Relational Similarity (State of the art)|Attributional and Relational Similarity]]<br />
* [[Automatic Summarization (State of the art)|Automatic Summarization]]<br />
* [[Chunking (State of the art)|Chunking]] (stub)<br />
* [[Dependency Parsing (State of the art)|Dependency Parsing]] (stub)<br />
* [[Document Classification (State of the art)|Document Classification]] (stub)<br />
* [[Language Identification (State of the art)|Language Identification]] (stub)<br />
* [[Named Entity Recognition (State of the art)|Named Entity Recognition]]<br />
* [[Noun-Modifier Semantic Relations (State of the art)|Noun-Modifier Semantic Relations]]<br />
* [[NP Chunking (State of the art)|NP Chunking]] <br />
* [[Paraphrase Identification (State of the art)|Paraphrase Identification]]<br />
* [[Parsing (State of the art)|Parsing]] <br />
* [[POS Induction (State of the art) |POS Induction]]<br />
* [[POS Tagging (State of the art) |POS Tagging]]<br />
* [[PP Attachment (State of the art)|PP Attachment]] (stub)<br />
* [[Semantic Role Labeling (State of the art)|Semantic Role Labeling]] (stub)<br />
* [[Sentiment Analysis (State of the art)|Sentiment Analysis]] (stub)<br />
* [[Speech Recognition (State of the art)|Speech Recognition]] (article request)<br />
* [[Temporal Expression Recognition and Normalisation (State of the art)|Temporal Expression Recognition and Normalisation]] (stub)<br />
* [[Cleaneval (State of the art)| Web Corpus Cleaning]] (stub)<br />
* [[Word Segmentation (State of the art)|Word Segmentation]] (stub)<br />
* [[Word Sense Disambiguation (State of the art)|Word Sense Disambiguation]] (stub)<br />
<!-- Please keep this list in alphabetical order --><br />
<br />
As a historical point of reference, you may want to refer to the [http://cslu.cse.ogi.edu/HLTsurvey/ Survey of the State of the Art in Human Language Technology] ([http://www.lt-world.org/HLT_Survey/master.pdf also available as PDF]), edited by R. Cole, J. Mariani, H. Uszkoreit, G. B. Varile, A. Zaenen, A. Zampolli, V. Zue, 1996.<br />
<br />
[[Category:State of the art]]</div>Auser