GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge
TL
TL;DR
This paper construct context-gloss pairs and propose three BERT based models for WSD and fine-tune the pre-trained BERT model to achieve new state-of-the-art results on WSD task.
Abstract
Word Sense Disambiguation (WSD) aims to find the exact sense of an ambiguous word in a particular context. Traditional supervised methods rarely take into consideration the lexical resources like WordNet, which are widely utilized in knowledge-based methods. Recent studies have shown the effectiveness of incorporating gloss (sense definition) into neural networks for WSD. However, compared with traditional word expert supervised methods, they have not achieved much improvement. In this paper, we focus on how to better leverage gloss knowledge in a supervised neural WSD system. We construct context-gloss pairs and propose three BERT based models for WSD. We fine-tune the pre-trained BERT model and achieve new state-of-the-art results on WSD task.
References20 items
1
Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation
2
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
3
Incorporating Glosses into Neural Word Sense Disambiguation
4
Deep Contextualized Word Representations
5