Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion

Olivier Ferret


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.
Anthology ID:
I17-1028
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
273–283
Language:
URL:
https://aclanthology.org/I17-1028
DOI:
Bibkey:
Cite (ACL):
Olivier Ferret. 2017. Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 273–283, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion (Ferret, IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/I17-1028.pdf