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
this https URL

本文探讨了不同的策略，将预训练的上下文化单词表示与非上下文化单词嵌入使用最佳策略相结合，其在多个基准 WSD 数据集上实现了显著比之前发表的最佳准确率更高的结果，并提供了源代码。