Disambiguating Distributional Neighbors Using a Lexical Substitution Dataset - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Disambiguating Distributional Neighbors Using a Lexical Substitution Dataset

Cécile Fabre
Nabil Hathout
Ludovic Tanguy

Résumé

This paper addresses the issue of polysemy in a distributional thesaurus. In such resources, distributional neighbors can relate indistinguishably to various senses. We propose a method to cluster the neighbors of a target word with respect to its senses, i.e. to attribute one sense to each neighbor. This is made possible by the use of a lexical substitution dataset, to which the distribution of the neighbors are compared.

Domaines

Linguistique
Fichier principal
Vignette du fichier
disambiguating-distributional-neighbors.pdf (171.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02054305 , version 1 (18-03-2019)

Identifiants

  • HAL Id : hal-02054305 , version 1

Citer

François Morlane-Hondère, Cécile Fabre, Nabil Hathout, Ludovic Tanguy. Disambiguating Distributional Neighbors Using a Lexical Substitution Dataset. 11th International Workshop on Natural Language Processing and Cognitive Science, Oct 2014, Venise, Italy. ⟨hal-02054305⟩
44 Consultations
83 Téléchargements

Partager

Gmail Facebook X LinkedIn More