Difference between revisions of "Parsing (State of the art)"

From ACL Wiki
Jump to: navigation, search
m (Wikipedia capitalization)
(Update links to newer versions)
 
(18 intermediate revisions by 7 users not shown)
Line 1: Line 1:
== "Standard" measure: ==
+
* '''Performance measure:''' PARSEVAL - the [http://nlp.cs.nyu.edu/evalb/ evalb] program
PARSEVAL -- the evalb[http://nlp.cs.nyu.edu/evalb/] program.
+
* '''Training data:''' sections 2-21 of Wall Street Journal corpus
 +
* '''Testing data:''' section 23 of Wall Street Journal corpus
  
== "Standard" datasets: ==
 
* Training: WSJ sections 2-22
 
* Testing: WSJ section 23
 
  
{{StateOfTheArtTable}}
+
== Table of results ==
  
| Johnson & Charniak's Parser  || Lexicalized N-Best PCFG + Discriminative re-reanking || Mark Johnson and Eugene Charniak, ACL 2005 [http://acl.ldc.upenn.edu/P/P05/P05-1022.pdf] || Available [http://www.cog.brown.edu/~mj/Software.htm] || 91.4 || Works well also on Brown
+
 
 +
{| border="1" cellpadding="5" cellspacing="1" width="100%"
 
|-
 
|-
| Collins' Parser || Lexicalized PCFG || Collins' Thesis [http://people.csail.mit.edu/mcollins/papers/thesis.ps], Bikel's Thesis [http://www.cis.upenn.edu/~dbikel/papers/thesis.pdf] || Dan Bikel's Implementation [http://www.cis.upenn.edu/~dbikel/software.html] || ??? ||  
+
! System name
 +
! Short description
 +
! Main publications
 +
! Software
 +
! Results (PARSEVAL)
 +
! Comments
 +
|-
 +
| Charniak & Johnson's Parser
 +
| Lexicalized N-Best PCFG + Discriminative reranking
 +
| Johnson and Charniak (2005)
 +
| [https://github.com/BLLIP/bllip-parser Download]
 +
| 91.4%
 +
| also works well on Brown
 +
|-
 +
| Self-trained Charniak & Johnson Parser
 +
| Above + self-training on ~2 million raw sentences from NANC
 +
| McClosky, Charniak, and Johnson (2006)
 +
| [http://nlp.stanford.edu/~mcclosky/selftraining.html Download]
 +
| 92.1%
 +
| also works well 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.
 +
 +
Charniak, E. and Johnson, M. (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.
 +
 +
McClosky, D., Charniak, E., and Johnson, M. (2006) [http://www.aclweb.org/anthology/N/N06/N06-1020.pdf Effective Self-Training for Parsing]. ''Proceedings of HLT/NAACL 2006'', pages 152-159, New York City, USA, June 2006.
 +
 +
Petrov, S., Barrett, L., Thibaux, R., and Klein, D. (2006). [http://nlp.cs.berkeley.edu/pubs/Petrov-Barrett-Thibaux-Klein_2006_Learning_paper.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://nlp.cs.berkeley.edu/pubs/Petrov-Klein_2007_Inference_paper.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]]
 
[[Category:State of the art]]

Latest revision as of 14:23, 28 October 2013

  • Performance measure: PARSEVAL - the evalb program
  • Training data: sections 2-21 of Wall Street Journal corpus
  • Testing data: section 23 of Wall Street Journal corpus


Table of results

System name Short description Main publications Software Results (PARSEVAL) Comments
Charniak & Johnson's Parser Lexicalized N-Best PCFG + Discriminative reranking Johnson and Charniak (2005) Download 91.4% also works well on Brown
Self-trained Charniak & Johnson Parser Above + self-training on ~2 million raw sentences from NANC McClosky, Charniak, and Johnson (2006) Download 92.1% also works well on Brown
Collins' Parser Lexicalized PCFG Collins (1999), Bikel (2004) Dan Bikel's implementation  ?  ?
Berkeley Parser Automatically induced PCFG Petrov et al. (2006), Petrov and Klein (2007) Berkeley Parser 90.1% works well also for Chinese and German
Link Grammar Dependency grammar Temperley, Sleator, Lafferty, others (1995-2006) Actively supported project  ? Persian, Arabic, Chinese, German, Russian dictionaries have been developed.

References

Bikel, D. (2004). On The Parameter Space of Generative Lexicalized Statistical Parsing Models. PhD Thesis, Computer and Information Science, University of Pennsylvania.

Collins, M. (1999). Head-driven Statistical Models for Natural Language Parsing. PhD Thesis, Computer and Information Science, University of Pennsylvania.

Charniak, E. and Johnson, M. (2005). 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.

McClosky, D., Charniak, E., and Johnson, M. (2006) Effective Self-Training for Parsing. Proceedings of HLT/NAACL 2006, pages 152-159, New York City, USA, June 2006.

Petrov, S., Barrett, L., Thibaux, R., and Klein, D. (2006). 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). Improved inference for unlexicalized parsing. Proceedings of NAACL 2007, pages 404-411.

Sleator, Daniel & Davy Temperly (1993) "Parsing English with a Link Grammar", Third International Workshop on Parsing Technologies.

See also


External links

  • PARSEVAL - the evalb program