@inproceedings{simonetti-etal-2024-subcategorization,
title = "Subcategorization of {I}talian Verbs with {LLM}s and {T}-{PAS}",
author = "Simonetti, Luca and
Jezek, Elisabetta and
Vetere, Guido",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.99/",
pages = "921--928",
ISBN = "979-12-210-7060-6",
abstract = "This study explores the application of Large Language Models (LLMs) to verb subcategorization in Italian, focusing on the identification and classification of syntactic patterns in sentences. While LLMs have made lexical analysis more implicit, explicit argument structure identification remains crucial in domain-specific contexts. The research leverages T-PAS, a rich lexical resource for Italian verbs, to fine-tune the open multilingual model Mistral 7B using the Iterative Reasoning Preference Optimization (IRPO) technique. This approach aims to enhance the recognition and extraction of verbal patterns from Italian sentences, addressing challenges in resource quality, coverage, and frame extraction methods. By combining curated lexical-semantic resources with neural language models, this work contributes to improving verb subcategorization tasks, particularly for the Italian language, and demonstrates the potential of LLMs in refining linguistic analysis tools."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonetti-etal-2024-subcategorization">
<titleInfo>
<title>Subcategorization of Italian Verbs with LLMs and T-PAS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Simonetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabetta</namePart>
<namePart type="family">Jezek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Vetere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</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">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>This study explores the application of Large Language Models (LLMs) to verb subcategorization in Italian, focusing on the identification and classification of syntactic patterns in sentences. While LLMs have made lexical analysis more implicit, explicit argument structure identification remains crucial in domain-specific contexts. The research leverages T-PAS, a rich lexical resource for Italian verbs, to fine-tune the open multilingual model Mistral 7B using the Iterative Reasoning Preference Optimization (IRPO) technique. This approach aims to enhance the recognition and extraction of verbal patterns from Italian sentences, addressing challenges in resource quality, coverage, and frame extraction methods. By combining curated lexical-semantic resources with neural language models, this work contributes to improving verb subcategorization tasks, particularly for the Italian language, and demonstrates the potential of LLMs in refining linguistic analysis tools.</abstract>
<identifier type="citekey">simonetti-etal-2024-subcategorization</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.99/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>921</start>
<end>928</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subcategorization of Italian Verbs with LLMs and T-PAS
%A Simonetti, Luca
%A Jezek, Elisabetta
%A Vetere, Guido
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F simonetti-etal-2024-subcategorization
%X This study explores the application of Large Language Models (LLMs) to verb subcategorization in Italian, focusing on the identification and classification of syntactic patterns in sentences. While LLMs have made lexical analysis more implicit, explicit argument structure identification remains crucial in domain-specific contexts. The research leverages T-PAS, a rich lexical resource for Italian verbs, to fine-tune the open multilingual model Mistral 7B using the Iterative Reasoning Preference Optimization (IRPO) technique. This approach aims to enhance the recognition and extraction of verbal patterns from Italian sentences, addressing challenges in resource quality, coverage, and frame extraction methods. By combining curated lexical-semantic resources with neural language models, this work contributes to improving verb subcategorization tasks, particularly for the Italian language, and demonstrates the potential of LLMs in refining linguistic analysis tools.
%U https://aclanthology.org/2024.clicit-1.99/
%P 921-928
Markdown (Informal)
[Subcategorization of Italian Verbs with LLMs and T-PAS](https://aclanthology.org/2024.clicit-1.99/) (Simonetti et al., CLiC-it 2024)
ACL