An analogical parser for restricted domains

Authors:
Donald Hindle
Affiliations:
AT&T Bell Labs, Murray Hill, NJ
Venue:
HLT '91 Proceedings of the workshop on Speech and Natural Language
Year:
1992

Citing 4
Cited 1

Toward memory-based reasoning

Communications of the ACM - Special issue on parallelism
Description theory and intonation boundaries

Cognitive models of speech processing
Parsing strategies with 'lexicalized' grammars: application to tree adjoining grammars

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
To parse or not to parse: relation-driven text skimming

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 2

Prediction of lexicalized tree fragments in text

HLT '93 Proceedings of the workshop on Human Language Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This note describes the current development of an approach to parsing designed to overcome some of the problems of existing parsers, particularly with respect to their utility as language models. The parser combines lexical and grammatical constraints into a uniform grammatical representation, is readily trainable (since the parser output is indistinguishable from the grammar input), and uses analogy to guess about the likelihood of constructions outside the grammar.