The LIGM-Alpage Architecture for the SPMRL 2013 Shared Task: Multiword Expression Analysis and Dependency Parsing

Abstract : This paper describes the LIGM-Alpage system for the SPMRL 2013 Shared Task. We only participated to the French part of the dependency parsing track, focusing on the realistic setting where the system is informed neither with gold tagging and morphology nor (more importantly) with gold grouping of tokens into multi-word expressions (MWEs). While the realistic scenario of predicting both MWEs and syntax has already been investigated for constituency parsing, the SPMRL 2013 shared task datasets offer the possibility to investigate it in the dependency framework. We obtain the best results for French, both for overall parsing and for MWE recognition, using a reparsing architecture that combines several parsers, with both pipeline architecture (MWE recognition followed by parsing), and joint architecture (MWE recognition performed by the parser).
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00932372
Contributor : Marie Candito <>
Submitted on : Thursday, January 16, 2014 - 6:48:50 PM
Last modification on : Friday, May 3, 2019 - 1:41:31 AM

Identifiers

  • HAL Id : hal-00932372, version 1

Citation

Mathieu Constant, Marie Candito, Djamé Seddah. The LIGM-Alpage Architecture for the SPMRL 2013 Shared Task: Multiword Expression Analysis and Dependency Parsing. Fourth Workshop on Statistical Parsing of Morphologically Rich Languages, Oct 2013, Seattle, United States. pp.46-52. ⟨hal-00932372⟩

Share

Metrics

Record views

470