@inproceedings{petersen-potts-2023-lexical,
title = "Lexical Semantics with Large Language Models: A Case Study of {E}nglish {``}break{''}",
author = "Petersen, Erika and
Potts, Christopher",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.36",
doi = "10.18653/v1/2023.findings-eacl.36",
pages = "490--511",
abstract = "Large neural language models (LLMs) can be powerful tools for research in lexical semantics. We illustrate this potential using the English verb {``}break{''}, which has numerous senses and appears in a wide range of syntactic frames. We show that LLMs capture known sense distinctions and can be used to identify informative new sense combinations for further analysis. More generally, we argue that LLMs are aligned with lexical semantic theories in providing high-dimensional, contextually modulated representations, but LLMs{'} lack of discrete features and dependence on usage-based data offer a genuinely new perspective on traditional problems in lexical semantics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petersen-potts-2023-lexical">
<titleInfo>
<title>Lexical Semantics with Large Language Models: A Case Study of English “break”</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Petersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Potts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large neural language models (LLMs) can be powerful tools for research in lexical semantics. We illustrate this potential using the English verb “break”, which has numerous senses and appears in a wide range of syntactic frames. We show that LLMs capture known sense distinctions and can be used to identify informative new sense combinations for further analysis. More generally, we argue that LLMs are aligned with lexical semantic theories in providing high-dimensional, contextually modulated representations, but LLMs’ lack of discrete features and dependence on usage-based data offer a genuinely new perspective on traditional problems in lexical semantics.</abstract>
<identifier type="citekey">petersen-potts-2023-lexical</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.36</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.36</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>490</start>
<end>511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexical Semantics with Large Language Models: A Case Study of English “break”
%A Petersen, Erika
%A Potts, Christopher
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F petersen-potts-2023-lexical
%X Large neural language models (LLMs) can be powerful tools for research in lexical semantics. We illustrate this potential using the English verb “break”, which has numerous senses and appears in a wide range of syntactic frames. We show that LLMs capture known sense distinctions and can be used to identify informative new sense combinations for further analysis. More generally, we argue that LLMs are aligned with lexical semantic theories in providing high-dimensional, contextually modulated representations, but LLMs’ lack of discrete features and dependence on usage-based data offer a genuinely new perspective on traditional problems in lexical semantics.
%R 10.18653/v1/2023.findings-eacl.36
%U https://aclanthology.org/2023.findings-eacl.36
%U https://doi.org/10.18653/v1/2023.findings-eacl.36
%P 490-511
Markdown (Informal)
[Lexical Semantics with Large Language Models: A Case Study of English “break”](https://aclanthology.org/2023.findings-eacl.36) (Petersen & Potts, Findings 2023)
ACL