@inproceedings{rovera-etal-2023-italian,
title = "{I}talian Legislative Text Classification for Gazzetta Ufficiale",
author = "Rovera, Marco and
Palmero Aprosio, Alessio and
Greco, Francesco and
Lucchese, Mariano and
Tonelli, Sara and
Antetomaso, Antonio",
editor = "Preo{\textcommabelow{t}}iuc-Pietro, Daniel and
Goanta, Catalina and
Chalkidis, Ilias and
Barrett, Leslie and
Spanakis, Gerasimos (Jerry) and
Aletras, Nikolaos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nllp-1.6",
doi = "10.18653/v1/2023.nllp-1.6",
pages = "44--50",
abstract = "This work introduces a novel, extensive annotated corpus for multi-label legislative text classification in Italian, based on legal acts from the Gazzetta Ufficiale, the official source of legislative information of the Italian state. The annotated dataset, which we released to the community, comprises over 363,000 titles of legislative acts, spanning over 30 years from 1988 until 2022. Moreover, we evaluate four models for text classification on the dataset, demonstrating how using only the acts{'} titles can achieve top-level classification performance, with a micro F1-score of 0.87. Also, our analysis shows how Italian domain-adapted legal models do not outperform general-purpose models on the task. Models{'} performance can be checked by users via a demonstrator system provided in support of this work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rovera-etal-2023-italian">
<titleInfo>
<title>Italian Legislative Text Classification for Gazzetta Ufficiale</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Rovera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Palmero Aprosio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Greco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariano</namePart>
<namePart type="family">Lucchese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Tonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Antetomaso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catalina</namePart>
<namePart type="family">Goanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="given">(Jerry)</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work introduces a novel, extensive annotated corpus for multi-label legislative text classification in Italian, based on legal acts from the Gazzetta Ufficiale, the official source of legislative information of the Italian state. The annotated dataset, which we released to the community, comprises over 363,000 titles of legislative acts, spanning over 30 years from 1988 until 2022. Moreover, we evaluate four models for text classification on the dataset, demonstrating how using only the acts’ titles can achieve top-level classification performance, with a micro F1-score of 0.87. Also, our analysis shows how Italian domain-adapted legal models do not outperform general-purpose models on the task. Models’ performance can be checked by users via a demonstrator system provided in support of this work.</abstract>
<identifier type="citekey">rovera-etal-2023-italian</identifier>
<identifier type="doi">10.18653/v1/2023.nllp-1.6</identifier>
<location>
<url>https://aclanthology.org/2023.nllp-1.6</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>44</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Italian Legislative Text Classification for Gazzetta Ufficiale
%A Rovera, Marco
%A Palmero Aprosio, Alessio
%A Greco, Francesco
%A Lucchese, Mariano
%A Tonelli, Sara
%A Antetomaso, Antonio
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%Y Goanta, Catalina
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Spanakis, Gerasimos (Jerry)
%Y Aletras, Nikolaos
%S Proceedings of the Natural Legal Language Processing Workshop 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F rovera-etal-2023-italian
%X This work introduces a novel, extensive annotated corpus for multi-label legislative text classification in Italian, based on legal acts from the Gazzetta Ufficiale, the official source of legislative information of the Italian state. The annotated dataset, which we released to the community, comprises over 363,000 titles of legislative acts, spanning over 30 years from 1988 until 2022. Moreover, we evaluate four models for text classification on the dataset, demonstrating how using only the acts’ titles can achieve top-level classification performance, with a micro F1-score of 0.87. Also, our analysis shows how Italian domain-adapted legal models do not outperform general-purpose models on the task. Models’ performance can be checked by users via a demonstrator system provided in support of this work.
%R 10.18653/v1/2023.nllp-1.6
%U https://aclanthology.org/2023.nllp-1.6
%U https://doi.org/10.18653/v1/2023.nllp-1.6
%P 44-50
Markdown (Informal)
[Italian Legislative Text Classification for Gazzetta Ufficiale](https://aclanthology.org/2023.nllp-1.6) (Rovera et al., NLLP-WS 2023)
ACL
- Marco Rovera, Alessio Palmero Aprosio, Francesco Greco, Mariano Lucchese, Sara Tonelli, and Antonio Antetomaso. 2023. Italian Legislative Text Classification for Gazzetta Ufficiale. In Proceedings of the Natural Legal Language Processing Workshop 2023, pages 44–50, Singapore. Association for Computational Linguistics.