Abstract

This paper describes a new statistical parser which is based on probabilities of dependencies between head-words in the parse tree. Standard bigram probability estimation techniques are extended to calculate probabilities of dependencies between pairs of words. Tests using Wall Street Journal data show that the method per- forms at least as well as SPATTER (Magerman 95; Jelinek et al. 94), which has the best published results for a statistical parser on this task. The simplicity of the approach means the model trains on 40,000 sentences in under 15 minutes. With a beam search strategy parsing speed can be improved to over 200 sentences a minute with negligible loss in accuracy.

Citations

649	A stochastic parts program and noun phrase parser for unrestricted text - Church - 1988
348	A maximum entropy model for part-of-speech tagging - Ratnaparkhi - 1996
337	Text chunking using transformation-based learning - Ramshaw, Marcus - 1995
302	Self-Organized Language Modeling for Speech Recognition - Jelinek - 1990
287	Statistical Decision-Tree Models for Parsing - Magerman - 1995
240	Inside-Outside Reestimation from Partially Bracketed Corpora - Pereira, Schabes - 1992
184	A Procedure for Quantitatively Comparing the Syntactic Coverage of English Grammars - Black - 1991
122	Prepositional Phrase Attachment through a Backed-off Model - Collins, Brooks - 1995
54	Pearl: A Probabilistic Chart Parser - Magerman, Marcus - 1991
5	Generalized LR Parsing of Natural Language (Corpora) with Unification-Based Grammars - Briscoe, Carroll - 1993
5	Decision Tree Parsing using a Hidden Derivation Model - Ratnaparkhi - 1994