Acceptability prediction by means of grammaticality quantification

Authors:
Philippe Blache;Barbara Hemforth;Stéphane Rauzy
Affiliations:
CNRS - Université de Provence, Aix-en-Provence, France;CNRS - Université de Provence, Aix-en-Provence, France;CNRS - Université de Provence, Aix-en-Provence, France
Venue:
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Year:
2006

Citing 3
Cited 3

Property grammars: a fully constraint-based theory

CSLP'04 Proceedings of the First international conference on Constraint Solving and Language Processing
Gradience, constructions and constraint systems

CSLP'04 Proceedings of the First international conference on Constraint Solving and Language Processing
Parsing unrestricted german text with defeasible constraints

CSLP'04 Proceedings of the First international conference on Constraint Solving and Language Processing

Grammar error detection with best approximated parse

IWPT '09 Proceedings of the 11th International Conference on Parsing Technologies
A model-theoretic framework for grammaticality judgements

FG'09 Proceedings of the 14th international conference on Formal grammar
Detecting human features in summaries --- symbol sequence statistical regularity

SETN'12 Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose in this paper a method for quantifying sentence grammaticality. The approach based on Property Grammars, a constraint-based syntactic formalism, makes it possible to evaluate a grammaticality index for any kind of sentence, including ill-formed ones. We compare on a sample of sentences the grammaticality indices obtained from PG formalism and the acceptability judgements measured by means of a psycholinguistic analysis. The results show that the derived grammaticality index is a fairly good tracer of acceptability scores.