A Vector Space for Distributional Semantics for Entailment
Abstract
Distributional semantics creates vector-space representations that capture many forms of semantic similarity, but their relation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation for a distributional semantics of entailment. Using a mean-field approximation, we develop approximate inference procedures and entailment operators over vectors of probabilities of features being known (versus unknown). We use this framework to reinterpret an existing distributional-semantic model (Word2Vec) as approximating an entailment-based model of the distributions of words in contexts, thereby predicting lexical entailment relations. In both unsupervised and semi-supervised experiments on hyponymy detection, we get substantial improvements over previous results.
Cite
@article{arxiv.1607.03780,
title = {A Vector Space for Distributional Semantics for Entailment},
author = {James Henderson and Diana Nicoleta Popa},
journal= {arXiv preprint arXiv:1607.03780},
year = {2016}
}
Comments
To appear in Proc. 54th Annual Meeting of the Association Computational Linguistics (ACL 2016)