Prediction of lexicalized tree fragments in text

Authors:
Donald Hindle
Affiliations:
AT&T Bell Laboratories, Murray Hill, NJ
Venue:
HLT '93 Proceedings of the workshop on Human Language Technology
Year:
1993

Citing 3
Cited 1

Parsing strategies with 'lexicalized' grammars: application to tree adjoining grammars

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
An analogical parser for restricted domains

HLT '91 Proceedings of the workshop on Speech and Natural Language
Semantic classes and syntactic ambiguity

HLT '93 Proceedings of the workshop on Human Language Technology

Disambiguation of super parts of speech (or supertags): almost parsing

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

There is a mismatch between the distribution of information in text, and a variety of grammatical formalisms for describing it, including ngrams, context-free grammars, and dependency grammars. Rather than adding probabilities to existing grammars, it is proposed to collect the distributions of flexibly sized partial trees. These can be used to enhance an ngram model, and in analogical parsing.