Repository logo
 

Injecting Lexical Contrast into Word Vectors by Guiding Vector Space Specialisation

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Vulić, I 
Korhonen, A 

Abstract

Word vector space specialisation models offer a portable, light-weight approach to fine-tuning arbitrary distributional vector spaces to discern between synonymy and antonymy. Their effectiveness is drawn from external linguistic constraints that specify the exact lexical relation between words. In this work, we show that a careful selection of the external constraints can steer and improve the specialisation. By simply selecting appropriate constraints, we report state-of-the-art results on a suite of tasks with well-defined benchmarks where modeling lexical contrast is crucial: 1) true semantic similarity, with highest reported scores on SimLex-999 and SimVerb-3500 to date; 2) detecting antonyms; and 3) distinguishing antonyms from synonyms.

Description

Keywords

Journal Title

Proceedings of the Annual Meeting of the Association for Computational Linguistics

Conference Name

Proceedings of the 3rd Workshop on Representation Learning for NLP

Journal ISSN

0736-587X

Volume Title

Publisher

Sponsorship
European Research Council (648909)