Abstract

We describe a parsing system based upon a language model for English that is, in turn, based upon assigning probabilities to possible parses for a sentence. This model is used in a parsing system by finding the parse for the sentence with the highest probability. This system outperforms previous schemes. As this is the third in a series of parsers by different authors that are similar enough to invite detailed comparisons but different enough to give rise to different levels of performance, we also report on some experiments designed to identify what aspects of these systems best explain their relative performance. Introduction We present a statistical parser that induces its grammar and probabilities from a hand-parsed corpus (a tree-bank). Parsers induced from corpora are of interest both as simply exercises in machine learning and also because they are often the best parsers obtainable by any method. That is, if one desires a parser that produces trees in the tree-bank ...

Citations

1654	B.: Building a large annotated corpus of english: The Penn treebank - Marcus, Marcinkiewicz, et al. - 1993
642	Accurate methods for the statistics of surprise and coincidence - Dunning - 1993
540	Class-based n-gram models of natural language - Brown, Pietra, et al. - 1992
477	Distributional clustering of english words - Pereira, Tishby, et al. - 1993
396	New Statistical Parser Based on Bigram Lexical De-pendencies - Collins - 2006
265	Structural ambiguity and lexical relations - Hindle, Rooth - 1993
240	Inside-Outside Reestimation from Partially Bracketed Corpora - Pereira, Schabes - 1992
203	Tree-Bank Grammars - Charniak - 1996
148	Towards History-based Grammars: Using Richer Models for Probabilistic Parsing - Black, Jelinek, et al. - 1993
145	Automatic acquisition of a large subcategorization dictionary from corpora - Manning - 1993
120	Automatic grammar induction and parsing free text: A transformationbased approach - Brill - 1993
101	Automatic Acquisition of Subcategorization Frames from Untagged Text - Brent - 1991
82	Two experiments on learning probabilistic dependency grammars from corpora - Carroll, Charniak - 1992
43	Efficiency, robustness, and accuracy in picky chart parsing - Magerman, Weir - 1992
40	Context-sensitive statistics for improved grammatical language models - Systems, Charniak, et al. - 1994
40	Lexicalized context-free grammars - Schabes, Waters - 1993
39	Parsing the Wall Street Journal with the Inside-Outside algorithm - Schabes, Roth, et al. - 1993
9	Expected-frequency interpolation - Charniak - 1996
6	Similarity-based Estimation of Word Cooccurences Probabilities. Meeting of the Association for Computational Linguistics - Dagan, Lee, et al. - 1994
2	Figures of merit for best- rst probabilistic chart parsing - Caraballo, Charniak - 1996
2	Statistical decision-tree models for parsing. InProceedings of the 33rd Annual Meeting of the Association for Computational Linguistics - MAGERMAN - 1995
1	A probabilistic parser and its applictions - Jones, Eisner - 1992