Using pseudo-senses for improving the extraction of synonyms from word embeddings - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Using pseudo-senses for improving the extraction of synonyms from word embeddings

Résumé

The methods proposed recently for specializing word embeddings according to a particular perspective generally rely on external knowledge. In this article, we propose Pseudofit, a new method for specializing word embeddings according to semantic similarity without any external knowledge. Pseudofit exploits the notion of pseudo-sense for building several representations for each word and uses these representations for making the initial embeddings more generic. We illustrate the interest of Pseudofit for acquiring synonyms and study several variants of Pseudofit according to this perspective
Fichier principal
Vignette du fichier
P18-2056.pdf (473.46 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

cea-04363091 , version 1 (23-12-2023)

Identifiants

Citer

Olivier Ferret. Using pseudo-senses for improving the extraction of synonyms from word embeddings. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Jul 2018, Melbourne, Australia. pp.351-357, ⟨10.18653/v1/P18-2056⟩. ⟨cea-04363091⟩
6 Consultations
4 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More