Using BERT for Word Sense Disambiguation
This work addresses a long-standing challenge in NLP for better language understanding, but it is incremental as it builds on existing BERT methods.
The paper tackled the problem of Word Sense Disambiguation (WSD) by using BERT to improve polyseme representations and achieved state-of-the-art results on the standard English All-word WSD evaluation.
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.