GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics

Mohammed Attia, Younes Samih, Manaal Faruqui, Wolfgang Maier


Abstract
This paper describes our system submission to the SemEval 2018 Task 10 on Capturing Discriminative Attributes. Given two concepts and an attribute, the task is to determine whether the attribute is semantically related to one concept and not the other. In this work we assume that discriminative attributes can be detected by discovering the association (or lack of association) between a pair of words. The hypothesis we test in this contribution is whether the semantic difference between two pairs of concepts can be treated in terms of measuring the distance between words in a vector space, or can simply be obtained as a by-product of word co-occurrence counts.
Anthology ID:
S18-1155
Volume:
Proceedings of the 12th International Workshop on Semantic Evaluation
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
947–952
Language:
URL:
https://aclanthology.org/S18-1155
DOI:
10.18653/v1/S18-1155
Bibkey:
Cite (ACL):
Mohammed Attia, Younes Samih, Manaal Faruqui, and Wolfgang Maier. 2018. GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 947–952, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics (Attia et al., SemEval 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/S18-1155.pdf