What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories
This addresses the challenge of understanding word senses in NLP, which is incremental as it applies existing models to a specific task with a novel prompting approach.
The paper tackled the problem of word sense disambiguation by prompting language models like BERT and RoBERTa to perform zero-shot WSD, casting it as a textual entailment problem using domain inventories, and achieved results close to supervised systems.
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.