Specialising Word Vectors for Lexical Entailment


Type
Conference Object
Change log
Authors
Vulic, I 
Mrkšić, N 
Abstract

We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation. By injecting external linguistic constraints (e.g., WordNet links) into the initial vector space, the LE specialisation procedure brings true hyponymy-hypernymy pairs closer together in the transformed Euclidean space. The proposed asymmetric distance measure adjusts the norms of word vectors to reflect the actual WordNet-style hierarchy of concepts. Simultaneously, a joint objective enforces semantic similarity using the symmetric cosine distance, yielding a vector space specialised for both lexical relations at once. LEAR specialisation achieves state-of-the-art performance in the tasks of hypernymy directionality, hypernymy detection, and graded lexical entailment, demonstrating the effectiveness and robustness of the proposed asymmetric specialisation model.

Description
Keywords
Journal Title
https://aclweb.org/anthology/volumes/proceedings-of-the-2018-conference-of-the-north-american-chapter-of-the-association-for-computational-linguistics-human-language-technologies-volume-1-long-papers/
Conference Name
16th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018)
Journal ISSN
Volume Title
1 (Long papers)
Publisher
Association for Computational Linguistics
Sponsorship
European Research Council (648909)