Learning attribute values in typed-unification grammars: on generalised rule reduction

Authors:
Liviu Ciortuz
Affiliations:
University of York, UK
Venue:
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Year:
2002

Citing 9
Cited 2

The logic of typed feature structures

The logic of typed feature structures
LIGHT - A Constraint Language and Compiler System for Typed-Unification Grammars

KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Efficient feature structure operations without compilation

Natural Language Engineering
Parser engineering and performance profiling

Natural Language Engineering
A compact architecture for dialogue management based on scripts and meta-outputs

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Ambiguity packing in constraint-based parsing: practical results

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
A structure-sharing representation for unification-based grammar formalisms

ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics
Categorial unification grammars

COLING '86 Proceedings of the 11th coference on Computational linguistics
Quasi-destructive graph unification with structure-sharing

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

LIGHT - A Constraint Language and Compiler System for Typed-Unification Grammars

KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
On two classes of feature paths in large-scale unification grammars

New developments in parsing technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present Generalised Reduction (GR), a learning technique for generalising attribute/feature values in typed-unification grammars. GR eliminates as many as possible of the feature constraints (FCs) from the type feature structures (FSs) while applying a criterion of preserving the parsing results on a given, training corpus. For parsing with GR-restricted rule FSs, and for checking the correctness of obtained parses on other corpora, one may use a new form FS unification which we call two-step unification to speed up parsing. We report results on a large-scale HPSG grammar for English.