论文信息 - K-best Spanning Tree Parsing

K-best Spanning Tree Parsing

This paper introduces a Maximum Entropy dependency parser based on an efficient kbest Maximum Spanning Tree (MST) algorithm. Although recent work suggests that the edge-factored constraints of the MST algorithm significantly inhibit parsing accuracy, we show that generating the 50-best parses according to an edge-factored model has an oracle performance well above the 1-best performance of the best dependency parsers. This motivates our parsing approach, which is based on reranking the kbest parses generated by an edge-factored model. Oracle parse accuracy results are presented for the edge-factored model and 1-best results for the reranker on eight languages (seven from CoNLL-X and English).

Keith Hall | K. Hall

[1] Francesco Maffioli,et al. The k best spanning arborescences of a network , 1980, Networks.

[2] Jason Eisner,et al. Three New Probabilistic Models for Dependency Parsing: An Exploration , 1996, COLING.

[3] Michael Collins,et al. A Statistical Parser for Czech , 1999, ACL.

[4] Mark Johnson,et al. Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques , 2002, ACL.

[5] Leo Breiman,et al. Bagging Predictors , 1996, Machine Learning.

[6] Eugene Charniak,et al. Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking , 2005, ACL.

[7] David Chiang,et al. Better k-best Parsing , 2005, IWPT.

[8] Fernando Pereira,et al. Non-Projective Dependency Parsing using Spanning Tree Algorithms , 2005, HLT.

[9] Koby Crammer,et al. Online Large-Margin Training of Dependency Parsers , 2005, ACL.

[10] Fernando Pereira,et al. Multilingual Dependency Analysis with a Two-Stage Discriminative Parser , 2006, CoNLL.

[11] Fernando Pereira,et al. Online Learning of Approximate Dependency Parsing Algorithms , 2006, EACL.

[12] Noah A. Smith,et al. Vine Parsing and Minimum Risk Reranking for Speed and Precision , 2006, CoNLL.

[13] Richard Johansson,et al. Extended Constituent-to-Dependency Conversion for English , 2007, NODALIDA.