Sense Embeddings in Knowledge-Based Word Sense Disambiguation

Loïc Vial (1, 2, 3) , Benjamin Lecouteux (1, 2, 3) , Didier Schwab (1, 2, 3)

1 UGA [2016-2019] - Université Grenoble Alpes [2016-2019]
2 LIG - Laboratoire d'Informatique de Grenoble
3 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole

In this paper, we develop a new way of creating sense vectors for any dictionary, by using an existing word embeddings model, and summing the vectors of the terms inside a sense's definition, weighted in function of their part of speech and their frequency. These vectors are then used for finding the closest senses to any other sense, thus creating a semantic network of related concepts, automatically generated. This network is hence evaluated against the existing semantic network found in WordNet, by comparing its contribution to a knowledge-based method for Word Sense Dis-ambiguation. This method can be applied to any other language which lacks such semantic network, as the creation of word vectors is totally unsupervised, and the creation of sense vectors only needs a traditional dictionary. The results show that our generated semantic network improves greatly the WSD system, almost as much as the manually created one.

Domaines: Traitement du texte et du document

Loïc Vial, Benjamin Lecouteux, Didier Schwab. Sense Embeddings in Knowledge-Based Word Sense Disambiguation. 12th International Conference on Computational Semantics, Sep 2017, Montpellier, France. ⟨hal-01599685⟩