Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations

Kentaro Kanada, Tetsunori Kobayashi, Yoshihiko Hayashi


Abstract
This paper proposes a method for classifying the type of lexical-semantic relation between a given pair of words. Given an inventory of target relationships, this task can be seen as a multi-class classification problem. We train a supervised classifier by assuming: (1) a specific type of lexical-semantic relation between a pair of words would be indicated by a carefully designed set of relation-specific similarities associated with the words; and (2) the similarities could be effectively computed by “sense representations” (sense/concept embeddings). The experimental results show that the proposed method clearly outperforms an existing state-of-the-art method that does not utilize sense/concept embeddings, thereby demonstrating the effectiveness of the sense representations.
Anthology ID:
W17-1905
Volume:
Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
SENSE
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
37–46
Language:
URL:
https://aclanthology.org/W17-1905
DOI:
10.18653/v1/W17-1905
Bibkey:
Cite (ACL):
Kentaro Kanada, Tetsunori Kobayashi, and Yoshihiko Hayashi. 2017. Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations. In Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications, pages 37–46, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations (Kanada et al., SENSE 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-1905.pdf