Context-gloss Augmentation for Improving Word Sense Disambiguation

TL;DR

This paper explores various data augmentation techniques, including back translation and hypernym gloss addition, to enhance BERT-based Word Sense Disambiguation, demonstrating significant performance improvements.

Contribution

It introduces and compares multiple context-gloss augmentation methods, highlighting the effectiveness of back translation and hypernym gloss addition for WSD.

Findings

Back translation on gloss yields the best performance.

Adding hypernyms' glosses improves WSD accuracy.

Sentence-level and word-level augmentations are both effective.

Abstract

The goal of Word Sense Disambiguation (WSD) is to identify the sense of a polysemous word in a specific context. Deep-learning techniques using BERT have achieved very promising results in the field and different methods have been proposed to integrate structured knowledge to enhance performance. At the same time, an increasing number of data augmentation techniques have been proven to be useful for NLP tasks. Building upon previous works leveraging BERT and WordNet knowledge, we explore different data augmentation techniques on context-gloss pairs to improve the performance of WSD. In our experiment, we show that both sentence-level and word-level augmentation methods are effective strategies for WSD. Also, we find out that performance can be improved by adding hypernyms' glosses obtained from a lexical knowledge base. We compare and analyze different context-gloss augmentation techniques, and the results show that applying back translation on gloss performs the best.