Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking

作者: Eugene Charniak , Mark Johnson

DOI: 10.3115/1219840.1219862

关键词:

摘要: Discriminative reranking is one method for constructing high-performance statistical parsers (Collins, 2000). A discriminative reranker requires a source of candidate parses each sentence. This paper describes simple yet novel sets 50-best based on coarse-to-fine generative parser (Charniak, generates lists that are substantially higher quality than previously obtainable. We used these as the input to MaxEnt (Johnson et al., 1999; Riezler 2002) selects best parse from set sentence, obtaining an f-score 91.0% sentences length 100 or less.

参考文章(18)
Steve Benson, Lois Curfman McInnes, Jorge J More, Jason Sarich, TAO users manual. Other Information: PBD: 2 Dec 2003. ,(2003) , 10.2172/822565
Víctor M. Jiménez, Andrés Marzal, Computation of the N Best Parse Trees for Weighted and Stochastic Context-Free Grammars Lecture Notes in Computer Science. pp. 183- 192 ,(2000) , 10.1007/3-540-44522-6_19
R. Schwartz, Y.-L. Chow, The N-best algorithms: an efficient and exact procedure for finding the N most likely sentence hypotheses international conference on acoustics, speech, and signal processing. pp. 81- 84 ,(1990) , 10.1109/ICASSP.1990.115542
Eugene Charniak, A maximum-entropy-inspired parser north american chapter of the association for computational linguistics. pp. 132- 139 ,(2000)
Joshua Goodman, Global Thresholding and Multiple Pass Parsing empirical methods in natural language processing. ,(1997)
Jane Grimshaw, Projection, heads, and optimality Linguistic Inquiry. ,vol. 28, pp. 373- 422 ,(1997)
Daniel M. Bikel, Intricacies of Collins' Parsing Model Computational Linguistics. ,vol. 30, pp. 479- 511 ,(2004) , 10.1162/0891201042544929
Michael Collins, Three generative, lexicalised models for statistical parsing Proceedings of the 35th annual meeting on Association for Computational Linguistics -. pp. 16- 23 ,(1997) , 10.3115/976909.979620
Liang Huang, David Chiang, Betterk-best parsing Proceedings of the Ninth International Workshop on Parsing Technology - Parsing '05. pp. 53- 64 ,(2005) , 10.3115/1654494.1654500