Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Conference Papers Year : 2017

Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion

Abstract

In this article, we propose to investigate a new problem consisting in turning a distributional thesaurus into dense word vectors. We propose more precisely a method for performing such task by associating graph embedding and distributed representation adaptation. We have applied and evaluated it for English nouns at a large scale about its ability to retrieve synonyms. In this context, we have also illustrated the interest of the developed method for three different tasks: the improvement of already existing word embeddings, the fusion of heterogeneous representations and the expansion of synsets
Fichier principal
Vignette du fichier
I17-1028 (212.74 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

cea-01857883 , version 1 (17-08-2018)

Identifiers

  • HAL Id : cea-01857883 , version 1

Cite

Olivier Ferret. Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion. Eighth International Joint Conference on Natural Language Processing (IJCNLP 2017), Nov 2017, Taipei, Taiwan. pp.273-283. ⟨cea-01857883⟩
113 View
116 Download

Share

Gmail Mastodon Facebook X LinkedIn More