From shallow to deep parsing using constraint satisfaction

Authors:
Jean-Marie Balfourier;Philippe Blache;Tristan van Rullen
Affiliations:
Laboratoire Parole et Langage, Aix-en-Provence, France;Laboratoire Parole et Langage, Aix-en-Provence, France;Laboratoire Parole et Langage, Aix-en-Provence, France
Venue:
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Year:
2002

Citing 5
Cited 1

From text to speech: the MITalk system

From text to speech: the MITalk system
Structural disambiguation with constraint propagation

ACL '90 Proceedings of the 28th annual meeting on Association for Computational Linguistics
Bottom-Up Filtering: a parsing strategy for GPSG

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 2
Topological dependency trees: a constraint-based account of linear precedence

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
From chunks to function-argument structure: a similarity-based approach

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics

Numbat: abolishing privileges when licensing new constituents in constraint-oriented parsing

CSLP '06 Proceedings of the Third Workshop on Constraints and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present in this paper a technique allowing to choose the parsing granularity within the same approach relying on a constraint-based formalism. Its main advantage lies in the fact that the same linguistic resources are used whatever the granularity. Such a method is useful in particular for systems such as text-to-speech that usually need a simple bracketing, but in some cases requires a precise syntactic structure. We illustrate this method in comparing the results for three different granularity levels and give some figures about their respective performance in parsing a tagged corpus.