Scoring Lexical Entailment with a Supervised Directional Similarity Network

Marek Rei, Daniela Gerz, Ivan Vulić


Abstract
We present the Supervised Directional Similarity Network, a novel neural architecture for learning task-specific transformation functions on top of general-purpose word embeddings. Relying on only a limited amount of supervision from task-specific scores on a subset of the vocabulary, our architecture is able to generalise and transform a general-purpose distributional vector space to model the relation of lexical entailment. Experiments show excellent performance on scoring graded lexical entailment, raising the state-of-the-art on the HyperLex dataset by approximately 25%.
Anthology ID:
P18-2101
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
638–643
Language:
URL:
https://aclanthology.org/P18-2101
DOI:
10.18653/v1/P18-2101
Bibkey:
Cite (ACL):
Marek Rei, Daniela Gerz, and Ivan Vulić. 2018. Scoring Lexical Entailment with a Supervised Directional Similarity Network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 638–643, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Scoring Lexical Entailment with a Supervised Directional Similarity Network (Rei et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/P18-2101.pdf
Presentation:
 P18-2101.Presentation.pdf
Video:
 https://vimeo.com/285805844
Data
HyperLex