Skip to Main content Skip to Navigation
Journal articles

Accounting for Contiguous Multiword Expressions in Shallow Parsing

Mathieu Constant 1 Olivier Blanc 2 Patrick Watrin 2
1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 Cental
Abstract : In this paper, we focus on chunking including contiguous multiword expression recognition, namely super-chunking. In particular, we present different strategies to improve a superchunker based on Conditional Random Fields by combining it with a finite-state symbolic super-chunker driven by lexical and grammatical resources. We display a substantial gain of 7.6 points in terms of overall accuracy.
Document type :
Journal articles
Complete list of metadata
https://hal-upec-upem.archives-ouvertes.fr/hal-00841563
Contributor : Matthieu Constant Connect in order to contact the contributor
Submitted on : Friday, July 5, 2013 - 10:43:44 AM
Last modification on : Tuesday, October 19, 2021 - 11:26:18 AM

Identifiers

  • HAL Id : hal-00841563, version 1

Collections

UPEC-UPEM | UNIV-MLV | PARISTECH | LIGM_LINGU | LIGM | ENPC | CNRS | LIGM_MOA

Citation

Mathieu Constant, Olivier Blanc, Patrick Watrin. Accounting for Contiguous Multiword Expressions in Shallow Parsing. The Prague Bulletin of Mathematical Linguistics, Univerzita Karlova v Praze, 2013, 99 (-), pp.59-75. ⟨hal-00841563⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

247