Language Models are the core for almost any Natural Language Processing system nowadays. One of their particularities is their contextualized representations, a game changer feature when a disambiguation between word senses is necessary. In this paper we aim to explore to what extent language models are capable of discerning among senses at inference time. We performed this analysis by prompting commonly used Languages Models such as BERT or RoBERTa to perform the task of Word Sense Disambiguation (WSD). We leverage the relation between word senses and domains, and cast WSD as a textual entailment problem, where the different hypothesis refer to the domains of the word senses. Our results show that this approach is indeed effective, close to supervised systems.
翻译:语言模型是当今几乎所有自然语言处理系统的核心。 语言模型的一个特点是其背景化的表达方式,当需要区分词感之间时,它是一个游戏变化的特征。 在本文中,我们的目标是探索语言模型在多大程度上能够辨别推论时间的感知。 我们通过推动通用语言模型,如BERT或RoBERTA来完成Word Sense Disamdiguation(WSD)的任务,我们利用文字感和域间的关系,并将WSD作为文字隐含问题,而不同的假设则指词感的范畴。我们的结果显示,这种方法确实有效,接近监督系统。