Word Sense Disambiguation (WSD) is a key task in Natural Language Processing (NLP), aiming to assign the correct meaning (sense) to a word in context. However, traditional WSD systems rely on WordNet as the underlying sense inventory, often differentiating meticulously between subtle nuances of word meanings, which may lead to excessive complexity and reduced practicality of WSD systems in today’s NLP. Indeed, current Pretrained Language Models (PLMs) do seem to be able to perform disambiguation, but it is not clear to what extent, or to what level of granularity, they actually operate. In this paper, we address these points and, firstly, introduce a new large-scale resource that leverages homonymy relations to systematically cluster WordNet senses, effectively reducing the granularity of word senses to a very coarse-grained level; secondly, we use this resource to train Homonymy Disambiguation systems and investigate whether PLMs are inherently able to differentiate coarse-grained word senses. Our findings demonstrate that, while state-of-the-art models still struggle to choose the correct fine-grained meaning of a word in context, Homonymy Disambiguation systems are able to differentiate homonyms with up to 95% accuracy scores even without fine-tuning the underlying PLM. We release our data and code at https://github.com/SapienzaNLP/homonymy-wsd.

Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models / Proietti, Lorenzo; Perrella, Stefano; Tedeschi, Simone; Vulpis, Giulia; Lavalle, Leonardo; Sanchietti, Andrea; Ferrari, Andrea; Navigli, Roberto. - (2024), pp. 924-938. (Intervento presentato al convegno 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) tenutosi a Torino; Italy).

Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models

Lorenzo Proietti
Primo
;
Stefano Perrella
Secondo
;
Simone Tedeschi
;
Giulia Vulpis
;
Leonardo Lavalle
;
Andrea Sanchietti
;
Andrea Ferrari
;
Roberto Navigli
Ultimo
2024

Abstract

Word Sense Disambiguation (WSD) is a key task in Natural Language Processing (NLP), aiming to assign the correct meaning (sense) to a word in context. However, traditional WSD systems rely on WordNet as the underlying sense inventory, often differentiating meticulously between subtle nuances of word meanings, which may lead to excessive complexity and reduced practicality of WSD systems in today’s NLP. Indeed, current Pretrained Language Models (PLMs) do seem to be able to perform disambiguation, but it is not clear to what extent, or to what level of granularity, they actually operate. In this paper, we address these points and, firstly, introduce a new large-scale resource that leverages homonymy relations to systematically cluster WordNet senses, effectively reducing the granularity of word senses to a very coarse-grained level; secondly, we use this resource to train Homonymy Disambiguation systems and investigate whether PLMs are inherently able to differentiate coarse-grained word senses. Our findings demonstrate that, while state-of-the-art models still struggle to choose the correct fine-grained meaning of a word in context, Homonymy Disambiguation systems are able to differentiate homonyms with up to 95% accuracy scores even without fine-tuning the underlying PLM. We release our data and code at https://github.com/SapienzaNLP/homonymy-wsd.
2024
2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Semantics; Word Sense Disambiguation; Corpus (Creation, Annotation, etc.)
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models / Proietti, Lorenzo; Perrella, Stefano; Tedeschi, Simone; Vulpis, Giulia; Lavalle, Leonardo; Sanchietti, Andrea; Ferrari, Andrea; Navigli, Roberto. - (2024), pp. 924-938. (Intervento presentato al convegno 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) tenutosi a Torino; Italy).
File allegati a questo prodotto
File Dimensione Formato  
Proietti_Analyzing_2024.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 798.95 kB
Formato Adobe PDF
798.95 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1711963
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact