What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories

Autor:	Sainz, Oscar, de Lacalle, Oier Lopez, Agirre, Eneko, Rigau, German
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Presented at GWC2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2302.03353 Zobrazit plný text záznamu View this record from Arxiv