@inproceedings{sainz-etal-2023-language,
title = "What do Language Models know about word senses? Zero-Shot {WSD} with Language Models and Domain Inventories",
author = "Sainz, Oscar and
de Lacalle, Oier Lopez and
Agirre, Eneko and
Rigau, German",
editor = "Rigau, German and
Bond, Francis and
Rademaker, Alexandre",
booktitle = "Proceedings of the 12th Global Wordnet Conference",
month = jan,
year = "2023",
address = "University of the Basque Country, Donostia - San Sebastian, Basque Country",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2023.gwc-1.40/",
pages = "331--342",
abstract = "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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sainz-etal-2023-language">
<titleInfo>
<title>What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="family">Sainz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oier</namePart>
<namePart type="given">Lopez</namePart>
<namePart type="family">de Lacalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Global Wordnet Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">University of the Basque Country, Donostia - San Sebastian, Basque Country</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">sainz-etal-2023-language</identifier>
<location>
<url>https://aclanthology.org/2023.gwc-1.40/</url>
</location>
<part>
<date>2023-01</date>
<extent unit="page">
<start>331</start>
<end>342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories
%A Sainz, Oscar
%A de Lacalle, Oier Lopez
%A Agirre, Eneko
%A Rigau, German
%Y Rigau, German
%Y Bond, Francis
%Y Rademaker, Alexandre
%S Proceedings of the 12th Global Wordnet Conference
%D 2023
%8 January
%I Global Wordnet Association
%C University of the Basque Country, Donostia - San Sebastian, Basque Country
%F sainz-etal-2023-language
%X 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.
%U https://aclanthology.org/2023.gwc-1.40/
%P 331-342
Markdown (Informal)
[What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories](https://aclanthology.org/2023.gwc-1.40/) (Sainz et al., GWC 2023)
ACL