Probabilistic Parsing using Left Corner Language Models

We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and bottom-up derivations. We develop the underlying theory and explain how a grammar can be induced from analyzed data. We show that the left-corner approach provides an advantage over simple top-down probabilistic context-free grammars in parsing the Wall Street Journal using a grammar induced from the Penn Treebank. We also conclude that the Penn Treebank provides a fairly weak tes bed due to the flatness of its bracketings and to the obvious overgeneration and undergeneration of its induced grammar.

[1]  Taylor L. Booth,et al.  Probabilistic Representation of Formal Languages , 1969, SWAT.

[2]  D. Sankoff.  Branching processes with terminal types: application to context-free grammars , 1971, Journal of Applied Probability.

[3]  J. Baker.  Trainable grammars for speech recognition , 1979 .

[4]  Steve Young,et al.  Applications of stochastic context-free grammars using the Inside-Outside algorithm , 1990 .

[5]  Ralph Grishman,et al.  A Procedure for Quantitatively Comparing the Syntactic Coverage of English Grammars , 1991, HLT.

[6]  Mats Rooth,et al.  Structural Ambiguity and Lexical Relations , 1991, ACL.

[7]  Julian Kupiec.  A Trellis-Based Algorithm For Estimating The Parameters Of Hidden Stochastic Context-Free Grammar , 1991, HLT.

[8]  Frederick Jelinek,et al.  Basic Methods of Probabilistic Context Free Grammars , 1992 .

[9]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[10]  Ted Briscoe,et al.  Generalized Probabilistic LR Parsing of Natural Language (Corpora) with Unification-Based Grammars , 1993, CL.

[11]  Mark-Jan Nederhof,et al.  Generalized Left-Corner Parsing , 1993, EACL.

[12]  Eugene Charniak,et al.  Statistical language learning , 1997 .

[13]  Yves Schabes,et al.  Parsing the Wall Street Journal with the Inside-Outside Algorithm , 1993, EACL.

[14]  Janyce Wiebe,et al.  Word-Sense Disambiguation Using Decomposable Models , 1994, ACL.

[15]  David M. Magerman.  Statistical Decision-Tree Models for Parsing , 1995, ACL.

[16]  Michael Collins,et al.  A New Statistical Parser Based on Bigram Lexical Dependencies , 1996, ACL.

[17]  Mark Lauer,et al.  Designing Statistical Language Learners: Experiments on Noun Compounds , 1996, ArXiv.

[18]  Eugene Charniak,et al.  Tree-Bank Grammars , 1996, AAAI/IAAI, Vol. 2.

[19]  Ted Briscoe,et al.  Apportioning Development Effort in a Probabilistic LR Parsing System Through Evaluation , 1996, EMNLP.

[20]  Michael Collins,et al.  Three Generative, Lexicalised Models for Statistical Parsing , 1997, ACL.

[21]  Yorick Wilks,et al.  Compacting the Penn Treebank Grammar , 1998, ACL.

[22]  Brian Roark,et al.  Efficient probabilistic top-down and left-corner parsing , 1999, ACL.

[23]  Mark Steedman,et al.  The nite connectivity of linguistic structure , 1999 .