@inproceedings{proietti-etal-2024-analyzing,
title = "Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models",
author = "Proietti, Lorenzo and
Perrella, Stefano and
Tedeschi, Simone and
Vulpis, Giulia and
Lavalle, Leonardo and
Sanchietti, Andrea and
Ferrari, Andrea and
Navigli, Roberto",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.83/",
pages = "924--938",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="proietti-etal-2024-analyzing">
<titleInfo>
<title>Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Proietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Perrella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Tedeschi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Vulpis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Lavalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Sanchietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Ferrari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">proietti-etal-2024-analyzing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.83/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>924</start>
<end>938</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models
%A Proietti, Lorenzo
%A Perrella, Stefano
%A Tedeschi, Simone
%A Vulpis, Giulia
%A Lavalle, Leonardo
%A Sanchietti, Andrea
%A Ferrari, Andrea
%A Navigli, Roberto
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F proietti-etal-2024-analyzing
%X 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.
%U https://aclanthology.org/2024.lrec-main.83/
%P 924-938
Markdown (Informal)
[Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models](https://aclanthology.org/2024.lrec-main.83/) (Proietti et al., LREC-COLING 2024)
ACL
- Lorenzo Proietti, Stefano Perrella, Simone Tedeschi, Giulia Vulpis, Leonardo Lavalle, Andrea Sanchietti, Andrea Ferrari, and Roberto Navigli. 2024. Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 924–938, Torino, Italia. ELRA and ICCL.