Using BERT for Word Sense Disambiguation

Abstract

Word Sense Disambiguation (WSD), which aims to identify the correct sense of a given polyseme, is a long-standing problem in NLP. In this paper, we propose to use BERT to extract better polyseme representations for WSD and explore several ways of combining BERT and the classifier. We also utilize sense definitions to train a unified classifier for all words, which enables the model to disambiguate unseen polysemes. Experiments show that our model achieves the state-of-the-art results on the standard English All-word WSD evaluation.

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Semi-supervised Word Sense Disambiguation with Neural Models

Cited by in corpus (7)

• Cross-lingual Word Sense Disambiguation using mBERT Embeddings with Syntactic Dependencies
• Incorporating Word Sense Disambiguation in Neural Language Models
• Context-gloss Augmentation for Improving Word Sense Disambiguation
• Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation
• Automatic Construction of Sememe Knowledge Bases via Dictionaries
• Tapping BERT for Preposition Sense Disambiguation
• Selection-based Question Answering of an MOOC