Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics

2017/10/06 by James Henderson, Henderson, James
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1710.02437

8 pages, 2 figures

arxiv created 2017/10/06 · openalex publication_date 2017/10/06 · arxiv updated 2017/10/09 · openalex created_date 2022/09/30 · openalex updated_date 2026/07/28

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.

Related

• A Vector Space for Distributional Semantics for Entailment
• Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment
• Distributional Models and Deep Learning Embeddings: Combining the Best of Both Worlds
• Using Distributional Thesaurus Embedding for Co-hyponymy Detection
• Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment