Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics
This addresses the fundamental issue of lexical entailment in natural language semantics, with incremental improvements in hyponymy prediction.
The paper tackled the problem of learning word embeddings for lexical entailment, specifically hyponymy, by proposing distributional semantic models that use a vector-space framework, and found that posterior vectors outperformed previous methods in unsupervised and semi-supervised experiments.
Lexical entailment, such as hyponymy, is a fundamental issue in the semantics of natural language. This paper proposes distributional semantic models which efficiently learn word embeddings for entailment, using a recently-proposed framework for modelling entailment in a vector-space. These models postulate a latent vector for a pseudo-phrase containing two neighbouring word vectors. We investigate both modelling words as the evidence they contribute about this phrase vector, or as the posterior distribution of a one-word phrase vector, and find that the posterior vectors perform better. The resulting word embeddings outperform the best previous results on predicting hyponymy between words, in unsupervised and semi-supervised experiments.