A Vector Space for Distributional Semantics for Entailment
This work addresses the challenge of capturing entailment relations in natural language processing, which is incremental as it builds on existing models like Word2Vec.
The paper tackles the problem of modeling semantic entailment in distributional semantics by proposing a vector-space model with approximate inference procedures and entailment operators, achieving substantial improvements in hyponymy detection experiments.
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.