Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics

TL;DR

This paper introduces a novel distributional semantic model that learns word embeddings for hyponymy by modeling entailment in vector space, leading to improved prediction of lexical hyponymy relations.

Contribution

It proposes a new entailment-based framework for learning word embeddings specifically tailored for hyponymy detection, outperforming previous models.

Findings

Embeddings outperform previous hyponymy prediction models.

Posterior vectors yield better results than evidence-based vectors.

Model performs well in both unsupervised and semi-supervised settings.

Abstract

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.