Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model

Goran Glavaš, Ivan Vulić


Abstract
We present a simple and effective feed-forward neural architecture for discriminating between lexico-semantic relations (synonymy, antonymy, hypernymy, and meronymy). Our Specialization Tensor Model (STM) simultaneously produces multiple different specializations of input distributional word vectors, tailored for predicting lexico-semantic relations for word pairs. STM outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages. We also show that, if coupled with a bilingual distributional space, the proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data.
Anthology ID:
N18-2029
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
181–187
Language:
URL:
https://aclanthology.org/N18-2029
DOI:
10.18653/v1/N18-2029
Bibkey:
Cite (ACL):
Goran Glavaš and Ivan Vulić. 2018. Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 181–187, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model (Glavaš & Vulić, NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2029.pdf
Dataset:
 N18-2029.Datasets.zip
Software:
 N18-2029.Software.zip
Code
 codogogo/stm