@inproceedings{manzi-etal-2024-fine,
title = "Fine-grained Sexism Detection in {I}talian Newspapers",
author = "Manzi, Federica and
Weber-Genzel, Leon and
Plank, Barbara",
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-1.66/",
pages = "556--583",
ISBN = "979-12-210-7060-6",
abstract = "In recent years, tasks revolving around hate speech detection have experienced a growing interest in the field of Natural Language Processing. Two main trends stand out in the context of sexism recognition: the focus on overt forms of sexism such as misogyny on social media and tackling the problem as a text classification task. The main objective of this work is to introduce a new approach to tackle sexism recognition as a sequence labelling task, operating on the token level rather than the document one. To achieve this goal, we introduce (i) the FGSDI (Fine-Grained Sexism Detection in Italian) corpus, containing Italian newspaper articles annotated with fine-grained linguistic markers of sexism, and (ii) a two-step pipeline that sequentially performs sexism detection on the sentence level and sexism classification on the token one. Our primary findings include that (i) tackling the task of sexism recognition as a sequence labelling task is possible, however, a large amount of labelled data is needed; (ii) leveraging few-shot learning for sexism detection proves to be an effective solution in scenarios where only a limited amount of data are available; (iii) the proposed pipeline approach allows for better results compared to the baseline by doubling the overall precision and achieving a better F1-score."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manzi-etal-2024-fine">
<titleInfo>
<title>Fine-grained Sexism Detection in Italian Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Manzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Weber-Genzel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</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>In recent years, tasks revolving around hate speech detection have experienced a growing interest in the field of Natural Language Processing. Two main trends stand out in the context of sexism recognition: the focus on overt forms of sexism such as misogyny on social media and tackling the problem as a text classification task. The main objective of this work is to introduce a new approach to tackle sexism recognition as a sequence labelling task, operating on the token level rather than the document one. To achieve this goal, we introduce (i) the FGSDI (Fine-Grained Sexism Detection in Italian) corpus, containing Italian newspaper articles annotated with fine-grained linguistic markers of sexism, and (ii) a two-step pipeline that sequentially performs sexism detection on the sentence level and sexism classification on the token one. Our primary findings include that (i) tackling the task of sexism recognition as a sequence labelling task is possible, however, a large amount of labelled data is needed; (ii) leveraging few-shot learning for sexism detection proves to be an effective solution in scenarios where only a limited amount of data are available; (iii) the proposed pipeline approach allows for better results compared to the baseline by doubling the overall precision and achieving a better F1-score.</abstract>
<identifier type="citekey">manzi-etal-2024-fine</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.66/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>556</start>
<end>583</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-grained Sexism Detection in Italian Newspapers
%A Manzi, Federica
%A Weber-Genzel, Leon
%A Plank, Barbara
%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 manzi-etal-2024-fine
%X In recent years, tasks revolving around hate speech detection have experienced a growing interest in the field of Natural Language Processing. Two main trends stand out in the context of sexism recognition: the focus on overt forms of sexism such as misogyny on social media and tackling the problem as a text classification task. The main objective of this work is to introduce a new approach to tackle sexism recognition as a sequence labelling task, operating on the token level rather than the document one. To achieve this goal, we introduce (i) the FGSDI (Fine-Grained Sexism Detection in Italian) corpus, containing Italian newspaper articles annotated with fine-grained linguistic markers of sexism, and (ii) a two-step pipeline that sequentially performs sexism detection on the sentence level and sexism classification on the token one. Our primary findings include that (i) tackling the task of sexism recognition as a sequence labelling task is possible, however, a large amount of labelled data is needed; (ii) leveraging few-shot learning for sexism detection proves to be an effective solution in scenarios where only a limited amount of data are available; (iii) the proposed pipeline approach allows for better results compared to the baseline by doubling the overall precision and achieving a better F1-score.
%U https://aclanthology.org/2024.clicit-1.66/
%P 556-583
Markdown (Informal)
[Fine-grained Sexism Detection in Italian Newspapers](https://aclanthology.org/2024.clicit-1.66/) (Manzi et al., CLiC-it 2024)
ACL
- Federica Manzi, Leon Weber-Genzel, and Barbara Plank. 2024. Fine-grained Sexism Detection in Italian Newspapers. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), pages 556–583, Pisa, Italy. CEUR Workshop Proceedings.