Difference between revisions of "Parsing (State of the art)"
Jump to navigation
Jump to search
| Line 15: | Line 15: | ||
| Johnson & Charniak's Parser | | Johnson & Charniak's Parser | ||
| Lexicalized N-Best PCFG + Discriminative re-reanking | | Lexicalized N-Best PCFG + Discriminative re-reanking | ||
| − | | | + | | Johnson and Charniak (2005) |
| − | | | + | | [http://www.cog.brown.edu/~mj/Software.htm download] |
| 91.4% | | 91.4% | ||
| works well also on Brown | | works well also on Brown | ||
| Line 35: | Line 35: | ||
|- | |- | ||
|} | |} | ||
| + | |||
| + | |||
| + | 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. | ||
[[Category:State of the art]] | [[Category:State of the art]] | ||
Revision as of 10:25, 27 June 2007
- 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
| 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' Thesis [1], Bikel's Thesis [2] | Dan Bikel's Implementation [3] | ??? | |
| Berkeley Parser | Automatically induced PCFG | Petrov, Barrett, Thibaux and Klein, ACL 2006 [4], Petrov and Klein, NAACL 2007 [5] | Available [6] | 90.1% | works well also for Chinese and German |
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.