Specialising Word Vectors for Lexical Entailment

TL;DR

This paper introduces LEAR, a post-processing method that transforms word vectors to better capture lexical entailment and hierarchical relations by integrating external lexical constraints, improving various hypernymy detection tasks.

Contribution

The paper proposes LEAR, a novel vector space specialisation technique that emphasizes lexical entailment and hierarchy, outperforming previous methods in hypernymy detection tasks.

Findings

Achieves state-of-the-art results in hypernymy detection

Effectively models lexical entailment and hierarchy

Robust across different lexical relation tasks

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.