Linguistic knowledge acquisition from parsing failures

Authors:
Masaki Kiyono;Jun-ichi Tsujii
Affiliations:
University of Manchester Institute of Science and Technology, Manchester, United Kingdom;University of Manchester Institute of Science and Technology, Manchester, United Kingdom
Venue:
EACL '93 Proceedings of the sixth conference on European chapter of the Association for Computational Linguistics
Year:
1993

Citing 5
Cited 4

Some chart-based techniques for parsing ill-formed input

ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
Chart parsing of robust grammars

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 1
TTP: a fast and robust parser for natural language

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 1
Towards robust PATR

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Linguistic knowledge generator

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2

Combination of symbolic and statistical approaches for grammatical knowledge acquisition

ANLC '94 Proceedings of the fourth conference on Applied natural language processing
Growing semantic grammars

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Hypothesis selection in grammar acquisition

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Lenient default unification for robust processing within unification based grammar formalisms

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

A semi-automatic procedure of linguistic knowledge acquisition is proposed, which combines corpus-based techniques with the conventional rule-based approach. The rule-based component generates all the possible hypotheses of defects which the existing linguistic knowledge might contain, when it fails to parse a sentence. The rule-based component does not try to identify the defects, but generates a set of hypotheses and the corpus-based component chooses the plausible ones among them. The procedure will be used for adapting or re-using existing linguistic resources for new application domains.