Learning Word Sense Embeddings from Word Sense Definitions

TL;DR

This paper introduces a novel method for learning word sense embeddings directly from definitions, improving the quality of sense representations for NLP tasks like similarity measurement and disambiguation.

Contribution

It proposes using word sense definitions instead of corpora to learn sense embeddings, addressing issues with polysemy and homonymy in traditional methods.

Findings

Sense embeddings outperform corpus-based methods in similarity tasks

High-quality embeddings improve word sense disambiguation accuracy

Approach demonstrates effectiveness across multiple NLP benchmarks

Abstract

Word embeddings play a significant role in many modern NLP systems. Since learning one representation per word is problematic for polysemous words and homonymous words, researchers propose to use one embedding per word sense. Their approaches mainly train word sense embeddings on a corpus. In this paper, we propose to use word sense definitions to learn one embedding per word sense. Experimental results on word similarity tasks and a word sense disambiguation task show that word sense embeddings produced by our approach are of high quality.