Abstract

In this paper we describe a new technique for parsing free text: a transformational grammar is automatically learned that is capable of accurately parsing text into binary-branching syntactic trees with nonterminals unlabelled. The algorithm works by beginning in a very naive state of knowledge about phrase structure. By repeatedly comparing the results of bracketing in the current state to proper bracketing provided in the training corpus, the system learns a set of simple structural transformations that can be applied to reduce error. After describing the algorithm, we present results and compare these results to other recent results in automatic grammar induction.

Citations

1654	B.: Building a large annotated corpus of english: The Penn treebank - Marcus, Marcinkiewicz, et al. - 1993
433	A simple rule-based part of speech tagger - Brill - 1992
316	The estimation of stochastic context-free grammars using the inside-outside algorithm. Computer Speech and Language - Lari, Young - 1990
240	Inside-Outside Reestimation from Partially Bracketed Corpora - Pereira, Schabes - 1992
158	A Corpus-Based Approach to Language Learning - Brill - 1993
81	The ATIS Spoken Language Systems pilot corpus - Hemphill, Godfrey, et al. - 1990
72	Parsing a natural language using mutual information statistics - Magerman, Marcus - 1990
39	Automatically acquiring phrase structure using distributional analysis - Brill, Marcus - 1992
38	Tagging an Unfamiliar Text With Minimal Human Supervision - Brill, Marcus - 1992
38	Robust Stochastic Parsing Using the Inside-Outside Algorithm - Briscoe, Waegner - 1992
32	Trainable grammars for speech recognition”. In Speech Communication Papers for the 97th Meeting of the Acoustical - Baker - 1979
29	Generating a grammar for statistical training - Sharman, Jelinek, et al. - 1990
24	Learning probabilistic dependency grammars from labeled text - Carroll, Charniak - 1992
12	A stochastic approach to parsing - Sampson - 1986
11	A Rule Based Approach to Prepositional Phrase Attachment Disambiguation - Brill, Resnik - 1994
11	et al. A Procedure for quantitatively comparing the syntactic coverage of English grammars - Black - 1991