A New Statistical Parser Based on Bigram Lexical Dependencies

DMCA

A New Statistical Parser Based on Bigram Lexical Dependencies (1996)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Michael John Collins

Citations:

487 - 4 self

BibTeX

@MISC{Collins96anew,
    author = {Michael John Collins},
    title = {A New Statistical Parser Based on Bigram Lexical Dependencies},
    year = {1996}
}

OpenURL

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.

Keyphrases

new statistical parser bigram lexical dependency negligible loss standard bigram probability estimation technique beam search strategy statistical parser model train wall street journal data show parse tree

DMCA