Strategies for Contiguous Multiword Expression Analysis and Dependency Parsing

Marie Candito (1) , Mathieu Constant (2)

1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
2 LIGM - Laboratoire d'Informatique Gaspard-Monge

In this paper, we investigate various strategies to predict both syntactic dependency parsing and contiguous multiword expression (MWE) recognition, testing them on the dependency version of French Treebank \cite{abeille:04}, as instantiated in the SPMRL Shared Task \cite{spmrl:st:2013}. Our work focuses on using an alternative representation of syntactically regular MWEs, which captures their syntactic internal structure. We obtain a system with comparable performance to that of previous works on this dataset, but which predicts both syntactic dependencies and the internal structure of MWEs. This can be useful for capturing the various degrees of semantic compositionality of MWEs.

Mots clés: statistical parsing; multi-word expressions

Domaines: Traitement du texte et du document

Marie Candito, Mathieu Constant. Strategies for Contiguous Multiword Expression Analysis and Dependency Parsing. ACL 14 - The 52nd Annual Meeting of the Association for Computational Linguistics, Jun 2014, Baltimore, United States. ⟨hal-01022415⟩