Skip to Main content Skip to Navigation
Conference papers

Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion

Olivier Ferret 1, 2, *
* Corresponding author
2 LVIC - Laboratoire Vision et Ingénierie des Contenus
DIASI - Département Intelligence Ambiante et Systèmes Interactifs : DRT/LIST/DIASI
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
Complete list of metadatas

https://hal-cea.archives-ouvertes.fr/cea-01857883
Contributor : Olivier Ferret <>
Submitted on : Friday, August 17, 2018 - 3:31:03 PM
Last modification on : Monday, February 10, 2020 - 6:13:48 PM

File

I17-1028
Files produced by the author(s)

Identifiers

  • HAL Id : cea-01857883, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

148

Files downloads

115