Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
This work addresses word sense disambiguation for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackled the problem of word sense disambiguation (WSD) by integrating pre-trained contextualized word representations, achieving accuracies that significantly exceed prior state-of-the-art results on multiple benchmark datasets.
Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering, named entity recognition, and sentiment analysis. However, evaluation on word sense disambiguation (WSD) in prior work shows that using contextualized word representations does not outperform the state-of-the-art approach that makes use of non-contextualized word embeddings. In this paper, we explore different strategies of integrating pre-trained contextualized word representations and our best strategy achieves accuracies exceeding the best prior published accuracies by significant margins on multiple benchmark WSD datasets. We make the source code available at https://github.com/nusnlp/contextemb-wsd.