A finite-state super-chunker

Authors:
Olivier Blanc;Matthieu Constant;Patrick Watrin
Affiliations:
Université de Marne-la-Vallée, Institut Gaspard Monge, France;Université de Marne-la-Vallée, Institut Gaspard Monge, France;Université de Marne-la-Vallée, Institut Gaspard Monge, France
Venue:
CIAA'07 Proceedings of the 12th international conference on Implementation and application of automata
Year:
2007

Citing 2
Cited 0

Partial parsing via finite-state cascades

Natural Language Engineering
Outilex, a linguistic platform for text processing

COLING-ACL '06 Proceedings of the COLING/ACL on Interactive presentation sessions

Quantified Score

Hi-index	0.00

Visualization

Abstract

Language is full of multiword unit expressions that form basic semantic units. The identification of these structures limits the combinatorial complexity induced by lexical ambiguity. In this paper, we detail an experiment that largely integrates these notions in a finite-state procedure of segmentation into super-chunks, preliminary to a parser. We show that the chunker, developped for French, reaches 92.9% precision and 98.7% recall.