ACL Wiki - User contributions [en]

Paraphrase Identification (State of the art)

2012-06-15T21:21:53Z

DesiLinguist: /* Table of results */

* '''source''': [http://research.microsoft.com/en-us/downloads/607D14D9-20CD-47E3-85BC-A2F65CD28042/default.aspx Microsoft Research Paraphrase Corpus] (MSRP)
* '''task''': given a pair of sentences, classify them as paraphrases or not paraphrases
* '''see''': Dolan et al. (2004)
* '''train''': 4,076 sentence pairs (2,753 positive: 67.5%)
* '''test''': 1,725 sentence pairs (1,147 positive: 66.5%)

== Sample data ==

* '''Sentence 1''': Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.
* '''Sentence 2''': Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.
* '''Class''': 1 (true paraphrase)

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! Algorithm
! Reference
! Description
! Accuracy
! F
|-
| FHS
| Finch et al. (2005)
| supervised combination of MT evaluation measures as features
| 75.0%
| 82.7%
|-
| KM
| Kozareva and Montoyo (2006)
| supervised combination of lexical and semantic features
| 76.6%
| 79.6%
|-
| RMLMG
| Rus et al. (2008)
| unsupervised graph subsumption
| 70.6%
| 80.5%
|-
| MCS
| Mihalcea et al. (2006)
| unsupervised combination of several word similarity measures
| 70.3%
| 81.3%
|-
| STS
| Islam and Inkpen (2007)
| unsupervised combination of semantic and string similarity
| 72.6%
| 81.3%
|-
| QKC
| Qiu et al. (2006)
| supervised sentence dissimilarity classification
| 72.0%
| 81.6%
|-
| matrixJcn
| Fernando and Stevenson (2008)
| unsupervised JCN WordNet similarity with matrix
| 74.1%
| 82.4%
|-
| WDDP
| Wan et al. (2006)
| supervised dependency-based features
| 75.6%
| 83.0%
|-
| SHPNM
| Socher et al. (2011)
| supervised recursive autoencoder with dynamic pooling
| 76.8%
| 83.6%
|-
| MTMETRICS
| Madnani et al. (2012)
| supervised combination of eight machine translation metrics
| 77.4%
| 84.1%
|-

|}

== References ==

Dolan, B., Quirk, C., and Brockett, C. (2004). [http://acl.ldc.upenn.edu/C/C04/C04-1051.pdf Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources], ''Proceedings of the 20th international conference on Computational Linguistics (COLING 2004)'', Geneva, Switzerland, pp. 350-356.

Fernando, S., and Stevenson, M. (2008). [http://www.dcs.shef.ac.uk/~samf/clukPaper.pdf A semantic similarity approach to paraphrase detection], ''Computational Linguistics UK (CLUK 2008) 11th Annual Research Colloquium''.

Finch, A., and H, Y.S., and Sumita, E. (2005). [http://aclweb.org/anthology/I/I05/I05-5003.pdf Using machine translation evaluation techniques to determine sentence-level semantic equivalence], "Proceedings of the Third International Workshop on Paraphrasing (IWP 2005)", Jeju Island, South Korea, pp. 17-24.

Islam, A., and Inkpen, D. (2007). [http://www.site.uottawa.ca/~diana/publications/ranlp_2007_textsim_camera_ready.pdf Semantic similarity of short texts], ''Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2007)'', Borovets, Bulgaria, pp. 291-297.

Kozareva, Z., and Montoyo, A. (2006). [http://www.dlsi.ua.es/~zkozareva/papers/fintalKozareva.pdf Paraphrase identification on the basis of supervised machine learning techniques], ''Advances in Natural Language Processing: 5th International Conference on NLP (FinTAL 2006)'', Turku, Finland, 524-533.

Mihalcea, R., Corley, C., and Strapparava, C. (2006). [http://reference.kfupm.edu.sa/content/c/o/corpus_based_and_knowledge_based_measure_3759629.pdf Corpus-based and knowledge-based measures of text semantic similarity], ''Proceedings of the National Conference on Artificial Intelligence (AAAI 2006)'', Boston, Massachusetts, pp. 775-780.

Qiu, L. and Kan, M.Y. and Chua, T.S. (2006). [http://acl.ldc.upenn.edu/W/W06/W06-1603.pdf Paraphrase recognition via dissimilarity significance classification], ''Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)'', pp. 18-26.

Rus, V. and McCarthy, P.M. and Lintean, M.C. and McNamara, D.S. and Graesser, A.C. (2008). [http://csep.psyc.memphis.edu/McNamara/pdf/Paraphrase_Identification.pdf Paraphrase identification with lexico-syntactic graph subsumption], ''FLAIRS 2008'', pp. 201-206.

Socher, R. and Huang, E.H., and Pennington, J. and Ng, A.Y., and Manning, C.D. (2011). [http://www.socher.org/uploads/Main/SocherHuangPenningtonNgManning_NIPS2011.pdf Dynamic pooling and unfolding recursive autoencoders for paraphrase detection], "Advances in Neural Information Processing Systems 24"

Wan, S., Dras, M., Dale, R., and Paris, C. (2006). [http://www.alta.asn.au/events/altw2006/proceedings/swan-final.pdf Using dependency-based features to take the "para-farce" out of paraphrase], ''Proceedings of the Australasian Language Technology Workshop (ALTW 2006)'', pp. 131-138.

Madnani, N., Tetreault, J., and Chodorow, M. (2012). [http://www.aclweb.org/anthology-new/N/N12/N12-1019.pdf Re-examining Machine Translation Metrics for Paraphrase Identification], ''Proceedings of 2012 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2012)'', pp. 182-190.

== See also ==

* [[State of the art]]

[[Category:State of the art]]

Paraphrase Identification (State of the art)

2012-06-15T21:21:26Z

DesiLinguist: /* References */

* '''source''': [http://research.microsoft.com/en-us/downloads/607D14D9-20CD-47E3-85BC-A2F65CD28042/default.aspx Microsoft Research Paraphrase Corpus] (MSRP)
* '''task''': given a pair of sentences, classify them as paraphrases or not paraphrases
* '''see''': Dolan et al. (2004)
* '''train''': 4,076 sentence pairs (2,753 positive: 67.5%)
* '''test''': 1,725 sentence pairs (1,147 positive: 66.5%)

== Sample data ==

* '''Sentence 1''': Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.
* '''Sentence 2''': Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.
* '''Class''': 1 (true paraphrase)

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! Algorithm
! Reference
! Description
! Accuracy
! F
|-
| FHS
| Finch et al. (2005)
| supervised combination of MT evaluation measures as features
| 75.0%
| 82.7%
|-
| KM
| Kozareva and Montoyo (2006)
| supervised combination of lexical and semantic features
| 76.6%
| 79.6%
|-
| RMLMG
| Rus et al. (2008)
| unsupervised graph subsumption
| 70.6%
| 80.5%
|-
| MCS
| Mihalcea et al. (2006)
| unsupervised combination of several word similarity measures
| 70.3%
| 81.3%
|-
| STS
| Islam and Inkpen (2007)
| unsupervised combination of semantic and string similarity
| 72.6%
| 81.3%
|-
| QKC
| Qiu et al. (2006)
| supervised sentence dissimilarity classification
| 72.0%
| 81.6%
|-
| matrixJcn
| Fernando and Stevenson (2008)
| unsupervised JCN WordNet similarity with matrix
| 74.1%
| 82.4%
|-
| WDDP
| Wan et al. (2006)
| supervised dependency-based features
| 75.6%
| 83.0%
|-
| SHPNM
| Socher et al. (2011)
| supervised recursive autoencoder with dynamic pooling
| 76.8%
| 83.6%
|-
| MTMETRICS
| Madnani et al. (2012)
| combining eight machine translation metrics in a classifier
| 77.4%
| 84.1%
|-

|}

== References ==

Dolan, B., Quirk, C., and Brockett, C. (2004). [http://acl.ldc.upenn.edu/C/C04/C04-1051.pdf Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources], ''Proceedings of the 20th international conference on Computational Linguistics (COLING 2004)'', Geneva, Switzerland, pp. 350-356.

Fernando, S., and Stevenson, M. (2008). [http://www.dcs.shef.ac.uk/~samf/clukPaper.pdf A semantic similarity approach to paraphrase detection], ''Computational Linguistics UK (CLUK 2008) 11th Annual Research Colloquium''.

Finch, A., and H, Y.S., and Sumita, E. (2005). [http://aclweb.org/anthology/I/I05/I05-5003.pdf Using machine translation evaluation techniques to determine sentence-level semantic equivalence], "Proceedings of the Third International Workshop on Paraphrasing (IWP 2005)", Jeju Island, South Korea, pp. 17-24.

Islam, A., and Inkpen, D. (2007). [http://www.site.uottawa.ca/~diana/publications/ranlp_2007_textsim_camera_ready.pdf Semantic similarity of short texts], ''Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2007)'', Borovets, Bulgaria, pp. 291-297.

Kozareva, Z., and Montoyo, A. (2006). [http://www.dlsi.ua.es/~zkozareva/papers/fintalKozareva.pdf Paraphrase identification on the basis of supervised machine learning techniques], ''Advances in Natural Language Processing: 5th International Conference on NLP (FinTAL 2006)'', Turku, Finland, 524-533.

Mihalcea, R., Corley, C., and Strapparava, C. (2006). [http://reference.kfupm.edu.sa/content/c/o/corpus_based_and_knowledge_based_measure_3759629.pdf Corpus-based and knowledge-based measures of text semantic similarity], ''Proceedings of the National Conference on Artificial Intelligence (AAAI 2006)'', Boston, Massachusetts, pp. 775-780.

Qiu, L. and Kan, M.Y. and Chua, T.S. (2006). [http://acl.ldc.upenn.edu/W/W06/W06-1603.pdf Paraphrase recognition via dissimilarity significance classification], ''Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)'', pp. 18-26.

Rus, V. and McCarthy, P.M. and Lintean, M.C. and McNamara, D.S. and Graesser, A.C. (2008). [http://csep.psyc.memphis.edu/McNamara/pdf/Paraphrase_Identification.pdf Paraphrase identification with lexico-syntactic graph subsumption], ''FLAIRS 2008'', pp. 201-206.

Socher, R. and Huang, E.H., and Pennington, J. and Ng, A.Y., and Manning, C.D. (2011). [http://www.socher.org/uploads/Main/SocherHuangPenningtonNgManning_NIPS2011.pdf Dynamic pooling and unfolding recursive autoencoders for paraphrase detection], "Advances in Neural Information Processing Systems 24"

Wan, S., Dras, M., Dale, R., and Paris, C. (2006). [http://www.alta.asn.au/events/altw2006/proceedings/swan-final.pdf Using dependency-based features to take the "para-farce" out of paraphrase], ''Proceedings of the Australasian Language Technology Workshop (ALTW 2006)'', pp. 131-138.

Madnani, N., Tetreault, J., and Chodorow, M. (2012). [http://www.aclweb.org/anthology-new/N/N12/N12-1019.pdf Re-examining Machine Translation Metrics for Paraphrase Identification], ''Proceedings of 2012 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2012)'', pp. 182-190.

== See also ==

* [[State of the art]]

[[Category:State of the art]]

Paraphrase Identification (State of the art)

2012-06-15T21:20:55Z

DesiLinguist: /* References */

* '''source''': [http://research.microsoft.com/en-us/downloads/607D14D9-20CD-47E3-85BC-A2F65CD28042/default.aspx Microsoft Research Paraphrase Corpus] (MSRP)
* '''task''': given a pair of sentences, classify them as paraphrases or not paraphrases
* '''see''': Dolan et al. (2004)
* '''train''': 4,076 sentence pairs (2,753 positive: 67.5%)
* '''test''': 1,725 sentence pairs (1,147 positive: 66.5%)

== Sample data ==

* '''Sentence 1''': Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.
* '''Sentence 2''': Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.
* '''Class''': 1 (true paraphrase)

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! Algorithm
! Reference
! Description
! Accuracy
! F
|-
| FHS
| Finch et al. (2005)
| supervised combination of MT evaluation measures as features
| 75.0%
| 82.7%
|-
| KM
| Kozareva and Montoyo (2006)
| supervised combination of lexical and semantic features
| 76.6%
| 79.6%
|-
| RMLMG
| Rus et al. (2008)
| unsupervised graph subsumption
| 70.6%
| 80.5%
|-
| MCS
| Mihalcea et al. (2006)
| unsupervised combination of several word similarity measures
| 70.3%
| 81.3%
|-
| STS
| Islam and Inkpen (2007)
| unsupervised combination of semantic and string similarity
| 72.6%
| 81.3%
|-
| QKC
| Qiu et al. (2006)
| supervised sentence dissimilarity classification
| 72.0%
| 81.6%
|-
| matrixJcn
| Fernando and Stevenson (2008)
| unsupervised JCN WordNet similarity with matrix
| 74.1%
| 82.4%
|-
| WDDP
| Wan et al. (2006)
| supervised dependency-based features
| 75.6%
| 83.0%
|-
| SHPNM
| Socher et al. (2011)
| supervised recursive autoencoder with dynamic pooling
| 76.8%
| 83.6%
|-
| MTMETRICS
| Madnani et al. (2012)
| combining eight machine translation metrics in a classifier
| 77.4%
| 84.1%
|-

|}

== References ==

Dolan, B., Quirk, C., and Brockett, C. (2004). [http://acl.ldc.upenn.edu/C/C04/C04-1051.pdf Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources], ''Proceedings of the 20th international conference on Computational Linguistics (COLING 2004)'', Geneva, Switzerland, pp. 350-356.

Fernando, S., and Stevenson, M. (2008). [http://www.dcs.shef.ac.uk/~samf/clukPaper.pdf A semantic similarity approach to paraphrase detection], ''Computational Linguistics UK (CLUK 2008) 11th Annual Research Colloquium''.

Finch, A., and H, Y.S., and Sumita, E. (2005). [http://aclweb.org/anthology/I/I05/I05-5003.pdf Using machine translation evaluation techniques to determine sentence-level semantic equivalence], "Proceedings of the Third International Workshop on Paraphrasing (IWP 2005)", Jeju Island, South Korea, pp. 17-24.

Islam, A., and Inkpen, D. (2007). [http://www.site.uottawa.ca/~diana/publications/ranlp_2007_textsim_camera_ready.pdf Semantic similarity of short texts], ''Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2007)'', Borovets, Bulgaria, pp. 291-297.

Kozareva, Z., and Montoyo, A. (2006). [http://www.dlsi.ua.es/~zkozareva/papers/fintalKozareva.pdf Paraphrase identification on the basis of supervised machine learning techniques], ''Advances in Natural Language Processing: 5th International Conference on NLP (FinTAL 2006)'', Turku, Finland, 524-533.

Mihalcea, R., Corley, C., and Strapparava, C. (2006). [http://reference.kfupm.edu.sa/content/c/o/corpus_based_and_knowledge_based_measure_3759629.pdf Corpus-based and knowledge-based measures of text semantic similarity], ''Proceedings of the National Conference on Artificial Intelligence (AAAI 2006)'', Boston, Massachusetts, pp. 775-780.

Qiu, L. and Kan, M.Y. and Chua, T.S. (2006). [http://acl.ldc.upenn.edu/W/W06/W06-1603.pdf Paraphrase recognition via dissimilarity significance classification], ''Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)'', pp. 18-26.

Rus, V. and McCarthy, P.M. and Lintean, M.C. and McNamara, D.S. and Graesser, A.C. (2008). [http://csep.psyc.memphis.edu/McNamara/pdf/Paraphrase_Identification.pdf Paraphrase identification with lexico-syntactic graph subsumption], ''FLAIRS 2008'', pp. 201-206.

Socher, R. and Huang, E.H., and Pennington, J. and Ng, A.Y., and Manning, C.D. (2011). [http://www.socher.org/uploads/Main/SocherHuangPenningtonNgManning_NIPS2011.pdf Dynamic pooling and unfolding recursive autoencoders for paraphrase detection], "Advances in Neural Information Processing Systems 24"

Wan, S., Dras, M., Dale, R., and Paris, C. (2006). [http://www.alta.asn.au/events/altw2006/proceedings/swan-final.pdf Using dependency-based features to take the "para-farce" out of paraphrase], ''Proceedings of the Australasian Language Technology Workshop (ALTW 2006)'', pp. 131-138.

Madnani, N., Tetreault, J., and Chodorow, M. (2012). [http://www.aclweb.org/anthology-new/N/N12/N12-1019.pdf], ''Proceedings of 2012 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2012)'', pp. 182-190.

== See also ==

* [[State of the art]]

[[Category:State of the art]]

Paraphrase Identification (State of the art)

2012-06-15T21:18:25Z

DesiLinguist: /* Table of results */

* '''source''': [http://research.microsoft.com/en-us/downloads/607D14D9-20CD-47E3-85BC-A2F65CD28042/default.aspx Microsoft Research Paraphrase Corpus] (MSRP)
* '''task''': given a pair of sentences, classify them as paraphrases or not paraphrases
* '''see''': Dolan et al. (2004)
* '''train''': 4,076 sentence pairs (2,753 positive: 67.5%)
* '''test''': 1,725 sentence pairs (1,147 positive: 66.5%)

== Sample data ==

* '''Sentence 1''': Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.
* '''Sentence 2''': Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.
* '''Class''': 1 (true paraphrase)

== Table of results ==

{| border="1" cellpadding="5" cellspacing="1" width="100%"
|-
! Algorithm
! Reference
! Description
! Accuracy
! F
|-
| FHS
| Finch et al. (2005)
| supervised combination of MT evaluation measures as features
| 75.0%
| 82.7%
|-
| KM
| Kozareva and Montoyo (2006)
| supervised combination of lexical and semantic features
| 76.6%
| 79.6%
|-
| RMLMG
| Rus et al. (2008)
| unsupervised graph subsumption
| 70.6%
| 80.5%
|-
| MCS
| Mihalcea et al. (2006)
| unsupervised combination of several word similarity measures
| 70.3%
| 81.3%
|-
| STS
| Islam and Inkpen (2007)
| unsupervised combination of semantic and string similarity
| 72.6%
| 81.3%
|-
| QKC
| Qiu et al. (2006)
| supervised sentence dissimilarity classification
| 72.0%
| 81.6%
|-
| matrixJcn
| Fernando and Stevenson (2008)
| unsupervised JCN WordNet similarity with matrix
| 74.1%
| 82.4%
|-
| WDDP
| Wan et al. (2006)
| supervised dependency-based features
| 75.6%
| 83.0%
|-
| SHPNM
| Socher et al. (2011)
| supervised recursive autoencoder with dynamic pooling
| 76.8%
| 83.6%
|-
| MTMETRICS
| Madnani et al. (2012)
| combining eight machine translation metrics in a classifier
| 77.4%
| 84.1%
|-

|}

== References ==

Dolan, B., Quirk, C., and Brockett, C. (2004). [http://acl.ldc.upenn.edu/C/C04/C04-1051.pdf Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources], ''Proceedings of the 20th international conference on Computational Linguistics (COLING 2004)'', Geneva, Switzerland, pp. 350-356.

Fernando, S., and Stevenson, M. (2008). [http://www.dcs.shef.ac.uk/~samf/clukPaper.pdf A semantic similarity approach to paraphrase detection], ''Computational Linguistics UK (CLUK 2008) 11th Annual Research Colloquium''.

Finch, A., and H, Y.S., and Sumita, E. (2005). [http://aclweb.org/anthology/I/I05/I05-5003.pdf Using machine translation evaluation techniques to determine sentence-level semantic equivalence], "Proceedings of the Third International Workshop on Paraphrasing (IWP 2005)", Jeju Island, South Korea, pp. 17-24.

Islam, A., and Inkpen, D. (2007). [http://www.site.uottawa.ca/~diana/publications/ranlp_2007_textsim_camera_ready.pdf Semantic similarity of short texts], ''Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2007)'', Borovets, Bulgaria, pp. 291-297.

Kozareva, Z., and Montoyo, A. (2006). [http://www.dlsi.ua.es/~zkozareva/papers/fintalKozareva.pdf Paraphrase identification on the basis of supervised machine learning techniques], ''Advances in Natural Language Processing: 5th International Conference on NLP (FinTAL 2006)'', Turku, Finland, 524-533.

Mihalcea, R., Corley, C., and Strapparava, C. (2006). [http://reference.kfupm.edu.sa/content/c/o/corpus_based_and_knowledge_based_measure_3759629.pdf Corpus-based and knowledge-based measures of text semantic similarity], ''Proceedings of the National Conference on Artificial Intelligence (AAAI 2006)'', Boston, Massachusetts, pp. 775-780.

Qiu, L. and Kan, M.Y. and Chua, T.S. (2006). [http://acl.ldc.upenn.edu/W/W06/W06-1603.pdf Paraphrase recognition via dissimilarity significance classification], ''Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)'', pp. 18-26.

Rus, V. and McCarthy, P.M. and Lintean, M.C. and McNamara, D.S. and Graesser, A.C. (2008). [http://csep.psyc.memphis.edu/McNamara/pdf/Paraphrase_Identification.pdf Paraphrase identification with lexico-syntactic graph subsumption], ''FLAIRS 2008'', pp. 201-206.

Socher, R. and Huang, E.H., and Pennington, J. and Ng, A.Y., and Manning, C.D. (2011). [http://www.socher.org/uploads/Main/SocherHuangPenningtonNgManning_NIPS2011.pdf Dynamic pooling and unfolding recursive autoencoders for paraphrase detection], "Advances in Neural Information Processing Systems 24"

Wan, S., Dras, M., Dale, R., and Paris, C. (2006). [http://www.alta.asn.au/events/altw2006/proceedings/swan-final.pdf Using dependency-based features to take the "para-farce" out of paraphrase], ''Proceedings of the Australasian Language Technology Workshop (ALTW 2006)'', pp. 131-138.

== See also ==

* [[State of the art]]

[[Category:State of the art]]

Conference acceptance rates

2012-04-11T12:36:59Z

DesiLinguist: /* CICLing */

==[[ACL]]==

=== Main Session ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>1997</td>
<td>264</td>
<td>83</td>
<td>24%</td>
</tr>
<tr>
<td>1998 (w/COLING)</td>
<td>550</td>
<td>137</td>
<td>25%</td>
</tr>
<tr>
<td>1999</td>
<td>320</td>
<td>80</td>
<td>25%</td>
</tr><tr>
<td>2000</td>
<td>267</td>
<td>70</td>
<td>26.2%</td>
</tr>
<tr>
<td>2001</td>
<td>260</td>
<td>69</td>
<td>27%</td>
</tr>
<tr>
<td>2002</td>
<td>256</td>
<td>66</td>
<td>26%</td>
</tr>
<tr>
<td>2003</td>
<td>360</td>
<td>71</td>
<td>20%</td>
</tr>
<tr>
<td>2004</td>
<td>348</td>
<td>88</td>
<td>25%</td>
</tr>
<tr>
<td>2005</td>
<td>423</td>
<td>77</td>
<td>18%</td>
</tr>
<tr>
<td>2006 (w/COLING)</td>
<td>630</td>
<td>147</td>
<td>23%</td>
</tr>
<tr>
<td>2007</td>
<td>588</td>
<td>131</td>
<td>22.3%</td>
</tr>
<tr>
<td>2008</td>
<td>470</td>
<td>119</td>
<td>25%</td>
</tr>
<tr>
<td>2009</td>
<td>569</td>
<td>121</td>
<td>21%</td>
</tr>
<tr>
<td>2010</td>
<td>638</td>
<td>160</td>
<td>25%</td>
</tr>
<tr>
<td>2011</td>
<td>634</td>
<td>164</td>
<td>26%</td>
</tr>
</table>

=== Student Session ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>1992</td>
<td>48</td>
<td>20</td>
<td>42%</td>
</tr>
<tr>
<td>1993</td>
<td>30</td>
<td>11</td>
<td>37%</td>
</tr>
<tr>
<td>1994</td>
<td>41</td>
<td>10</td>
<td>24%</td>
</tr>
<tr>
<td>1995</td>
<td>48</td>
<td>19</td>
<td>24%</td>
</tr>
<tr>
<td>1996</td>
<td>32</td>
<td>14</td>
<td>44%</td>
</tr>
<tr>
<td>1997</td>
<td>42</td>
<td>10</td>
<td>24%</td>
</tr>
<tr>
<td>1998</td>
<td>46</td>
<td>12</td>
<td>26%</td>
</tr>
<tr>
<td>1999</td>
<td>30</td>
<td>10</td>
<td>33%</td>
</tr>
<tr>
<td>2000</td>
<td>36</td>
<td>10</td>
<td>28%</td>
</tr>
<tr>
<td>2005</td>
<td>70</td>
<td>26</td>
<td>37%</td>
</tr>
<tr>
<td>2006</td>
<td>40</td>
<td>15</td>
<td>38%</td>
</tr>
<tr>
<td>2007</td>
<td>52</td>
<td>16</td>
<td>31%</td>
</tr>
<tr>
<td>2008</td>
<td>27</td>
<td>12</td>
<td>44%</td>
</tr>
<tr>
<td>2009</td>
<td>25</td>
<td>12</td>
<td>48%</td>
</tr>
</table>

=== Posters/Short Papers ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2005</td>
<td>56</td>
<td>31</td>
<td>55%</td>
</tr>
<tr>
<td>2006</td>
<td>630</td>
<td>125</td>
<td>20%</td>
</tr>
<tr>
<td>2007</td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td>2008</td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td>2009</td>
<td>356</td>
<td>93</td>
<td>26%</td>
</tr>
<tr>
<td>2010</td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td>2011</td>
<td>512</td>
<td>128</td>
<td>25%</td>
</tr>
</table>

==[[CICLing]]==

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2000</td>
<td>??</td>
<td>29</td>
<td>??</td>
</tr>
<tr>
<td>2001</td>
<td>72</td>
<td>41</td>
<td>57%</td>
</tr>
<tr>
<td>2002</td>
<td>67</td>
<td>35</td>
<td>52%</td>
</tr>
<tr>
<td>2003</td>
<td>92</td>
<td>43</td>
<td>46%</td>
</tr>
<tr>
<td>2004</td>
<td>129</td>
<td>40</td>
<td>31%</td>
</tr>
<tr>
<td>2005</td>
<td>151</td>
<td>53</td>
<td>35%</td>
</tr>
<tr>
<td>2006</td>
<td>176 (141 full + 35 short)</td>
<td>59 (43 full + 16 short)</td>
<td>30.4% full & 45.7% short</td>
</tr>
<tr>
<td>2007</td>
<td>179</td>
<td>53</td>
<td>29.6%</td>
</tr>
<tr>
<td>2008</td>
<td>204</td>
<td>52</td>
<td>25.5%</td>
</tr>
<tr>
<td>2009</td>
<td>167</td>
<td>44</td>
<td>26.3%</td>
</tr>
<tr>
<td>2010</td>
<td>271</td>
<td>61</td>
<td>22.5%</td>
</tr>
<tr>
<td>2012</td>
<td>307</td>
<td>88</td>
<td>28.6%</td>
</tr>
</table>

==[[COLING]]==

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>1998</td>
<td>550</td>
<td>137</td>
<td>25%</td>
</tr>
<tr>
<td>2000</td>
<td>323</td>
<td>110</td>
<td>34%</td>
</tr>
<tr>
<td>2006</td>
<td>630</td>
<td>147</td>
<td>23%</td>
</tr>
<tr>
<td>2008</td>
<td>600</td>
<td>145</td>
<td>24%</td>
</tr>
<tr>
<td>2010</td>
<td>815</td>
<td>334</td>
<td>41%</td>
</tr>
</table>

==[[CONLL]]==

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2003</td>
<td>35</td>
<td>17</td>
<td>48.6%</td>
</tr>
<tr>
<td>2004</td>
<td>23</td>
<td>11</td>
<td>47.8%</td>
</tr>
<tr>
<td>2005</td>
<td>70</td>
<td>19</td>
<td>27%</td>
</tr>
</table>

==[[EACL]]==

=== Main Session ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2003</td>
<td>?</td>
<td>?</td>
<td>26.5%</td>
</tr>
<tr>
<td>2006</td>
<td>264</td>
<td>52</td>
<td>20%</td>
</tr>
<tr>
<td>2009</td>
<td>360</td>
<td>100</td>
<td>28%</td>
</tr>
<tr>
<td>2012</td>
<td>314</td>
<td>?</td>
<td>27%</td>
</tr>
</table>

=== Demonstration Papers ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2012</td>
<td>37</td>
<td>21</td>
<td>57%</td>
</tr>
</table>

=== Student Session ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>1993</td>
<td>34</td>
<td>6</td>
<td>18%</td>
</tr>
<tr>
<td>1995</td>
<td>37</td>
<td>8</td>
<td>22%</td>
</tr>
<tr>
<td>1997</td>
<td>42</td>
<td>10</td>
<td>24%</td>
</tr><tr>
<td>1999</td>
<td>17</td>
<td>8</td>
<td>47%</td>
</tr>
<tr>
<td>2003</td>
<td>18</td>
<td>6</td>
<td>33.3%</td>
</tr>
<tr>
<td>2006</td>
<td>33</td>
<td>9</td>
<td>27%</td>
</tr>
<tr>
<td>2009</td>
<td>38</td>
<td>11</td>
<td>29%</td>
</tr>
<tr>
<td>2012</td>
<td>38</td>
<td>10</td>
<td>26%</td>
</tr>
</table>

==[[EMNLP]]==

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>1997</td>
<td>??</td>
<td>??</td>
<td>35%</td>
</tr>
<tr>
<td>2002</td>
<td>142</td>
<td>35</td>
<td>25%</td>
</tr>
<tr>
<td>2003</td>
<td>???</td>
<td>28</td>
<td>??%</td>
</tr>
<tr>
<td>2004</td>
<td>247</td>
<td>58</td>
<td>24%</td>
</tr>
<tr>
<td>2005</td>
<td>402</td>
<td>127</td>
<td>32%</td>
</tr>
<tr>
<td>2006</td>
<td>234</td>
<td>73</td>
<td>31%</td>
</tr>
<tr>
<td>2007</td>
<td>398</td>
<td>109</td>
<td>27%</td>
</tr>
<tr>
<td>2008</td>
<td>385</td>
<td>116</td>
<td>30%</td>
</tr>
<tr>
<td>2009</td>
<td>475</td>
<td>163</td>
<td>34%</td>
</tr>
<tr>
<td>2010</td>
<td>500</td>
<td>125</td>
<td>25%</td>
</tr>
<tr>
<td>2011</td>
<td>628</td>
<td>149</td>
<td>24%</td>
</tr>
</table>

==[[NAACL HLT]]==

=== Main Session ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2000</td>
<td>166</td>
<td>43</td>
<td>26%</td>
</tr>
<tr>
<td>2001</td>
<td>110</td>
<td>31</td>
<td>28%</td>
</tr>
<tr>
<td>2002</td>
<td>141</td>
<td>28</td>
<td>20%</td>
</tr>
<tr>
<td>2003</td>
<td>162</td>
<td>37</td>
<td>23%</td>
</tr>
<tr>
<td>2004</td>
<td>168</td>
<td>43</td>
<td>26%</td>
</tr>
<tr>
<td>2005</td>
<td>402</td>
<td>127</td>
<td>32%</td>
</tr>
<tr>
<td>2006</td>
<td>257</td>
<td>62</td>
<td>24%</td>
</tr>
<tr>
<td>2007</td>
<td>298</td>
<td>72</td>
<td>24%</td>
</tr>
<tr>
<td>2008</td>
<td>470</td>
<td>119</td>
<td>25%</td>
</tr>
<tr>
<td>2009</td>
<td>260</td>
<td>75</td>
<td>29%</td>
</tr>
<tr>
<td>2010</td>
<td>291</td>
<td>90</td>
<td>31%</td>
</tr>
<tr>
<td>2011</td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td>2012</td>
<td>199</td>
<td></td>
<td></td>
</tr>

</table>

=== Student Session ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2009</td>
<td>29</td>
<td>17</td>
<td>59%</td>
</tr>
</table>

==[[IJCNLP]]==

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2004</td>
<td>211</td>
<td>66</td>
<td>31%</td>
</tr>
<tr>
<td>2005</td>
<td>289</td>
<td>90</td>
<td>31%</td>
</tr>
<tr>
<td>2008</td>
<td>270</td>
<td>75</td>
<td>28%</td>
</tr>
<tr>
<td>2009</td>
<td>569</td>
<td>121</td>
<td>21%</td>
</tr>
<tr>
<td>2011</td>
<td>478</td>
<td>176</td>
<td>36%</td>
</tr>
</table>

==[[IWCS]]==

=== Long Papers ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2011</td>
<td>72</td>
<td>30</td>
<td>42%</td>
</tr>
</table>

=== Short Papers ===

<table cellspacing="1" cellpadding="1" border="1" width="20%">
<tr>
<th>Year</th>
<th>Submitted</th>
<th>Accepted</th>
<th>Rate</th>
</tr>
<tr>
<td>2011</td>
<td>38</td>
<td>20</td>
<td>53%</td>
</tr>
</table>

[[Category:Conferences]]