Parsing (State of the art)

• Performance measure: PARSEVAL - the evalb program
• Training data: sections 2-22 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
Johnson & Charniak's Parser	Lexicalized N-Best PCFG + Discriminative re-reanking	Johnson and Charniak (2005)	download	91.4%	works well also 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.

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

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.

See also

• State of the art

External links

• PARSEVAL - the evalb program