Latent Vector Weighting for Word Meaning in Context

Tim van de Cruys (1) , Thierry Poibeau (2) , Anna Korhonen (3)

1 RCEAL - Research Centre for English and Applied Linguistics
2 Lattice - Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094
3 Computer Laboratory [Cambridge]

This paper presents a novel method for the computation of word meaning in context. We make use of a factorization model in which words, together with their window-based context words and their dependency relations, are linked to latent dimensions. The factorization model allows us to determine which dimensions are important for a particular context, and adapt the dependency-based feature vector of the word accordingly. The evaluation on a lexical substitution task - carried out for both English and French - indicates that our approach is able to reach better results than state-of-the-art methods in lexical substitution, while at the same time providing more accurate meaning representations.

Domaines: Traitement du texte et du document; Apprentissage [cs.LG]; Informatique; Linguistique; Linguistique

Tim van de Cruys, Thierry Poibeau, Anna Korhonen. Latent Vector Weighting for Word Meaning in Context. Empirical Methods in Natural Language Processing, 2011, France. ⟨hal-00666475⟩