@inproceedings{vallecillo-rodriguez-etal-2024-conan-mt,
title = "{CONAN}-{MT}-{SP}: A {S}panish Corpus for Counternarrative Using {GPT} Models",
author = "Vallecillo Rodr{\'\i}guez, Mar{\'\i}a Estrella and
Cantero Romero, Maria Victoria and
Cabrera De Castro, Isabel and
Montejo R{\'a}ez, Arturo and
Mart{\'\i}n Valdivia, Mar{\'\i}a Teresa",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.326",
pages = "3677--3688",
abstract = "This paper describes the automated generation of CounterNarratives (CNs) for Hate Speech (HS) in Spanish using GPT-based models. Our primary objective is to evaluate the performance of these models in comparison to human capabilities. For this purpose, the English CONAN Multitarget corpus is taken as a starting point and we use the DeepL API to automatically translate into Spanish. Two GPT-based models, GPT-3 and GPT-4, are applied to the HS segment through a few-shot prompting strategy to generate a new CN. As a consequence of our research, we have created a high quality corpus in Spanish that includes the original HS-CN pairs translated into Spanish, in addition to the CNs generated automatically with the GPT models and that have been evaluated manually. The resulting CONAN-MT-SP corpus and its evaluation will be made available to the research community, representing the most extensive linguistic resource of CNs in Spanish to date. The results demonstrate that, although the effectiveness of GPT-4 outperforms GPT-3, both models can be used as systems to automatically generate CNs to combat the HS. Moreover, these models consistently outperform human performance in most instances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vallecillo-rodriguez-etal-2024-conan-mt">
<titleInfo>
<title>CONAN-MT-SP: A Spanish Corpus for Counternarrative Using GPT Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="given">Estrella</namePart>
<namePart type="family">Vallecillo Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Cantero Romero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Cabrera De Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo Ráez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Martín Valdivia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the automated generation of CounterNarratives (CNs) for Hate Speech (HS) in Spanish using GPT-based models. Our primary objective is to evaluate the performance of these models in comparison to human capabilities. For this purpose, the English CONAN Multitarget corpus is taken as a starting point and we use the DeepL API to automatically translate into Spanish. Two GPT-based models, GPT-3 and GPT-4, are applied to the HS segment through a few-shot prompting strategy to generate a new CN. As a consequence of our research, we have created a high quality corpus in Spanish that includes the original HS-CN pairs translated into Spanish, in addition to the CNs generated automatically with the GPT models and that have been evaluated manually. The resulting CONAN-MT-SP corpus and its evaluation will be made available to the research community, representing the most extensive linguistic resource of CNs in Spanish to date. The results demonstrate that, although the effectiveness of GPT-4 outperforms GPT-3, both models can be used as systems to automatically generate CNs to combat the HS. Moreover, these models consistently outperform human performance in most instances.</abstract>
<identifier type="citekey">vallecillo-rodriguez-etal-2024-conan-mt</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.326</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3677</start>
<end>3688</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CONAN-MT-SP: A Spanish Corpus for Counternarrative Using GPT Models
%A Vallecillo Rodríguez, María Estrella
%A Cantero Romero, Maria Victoria
%A Cabrera De Castro, Isabel
%A Montejo Ráez, Arturo
%A Martín Valdivia, María Teresa
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F vallecillo-rodriguez-etal-2024-conan-mt
%X This paper describes the automated generation of CounterNarratives (CNs) for Hate Speech (HS) in Spanish using GPT-based models. Our primary objective is to evaluate the performance of these models in comparison to human capabilities. For this purpose, the English CONAN Multitarget corpus is taken as a starting point and we use the DeepL API to automatically translate into Spanish. Two GPT-based models, GPT-3 and GPT-4, are applied to the HS segment through a few-shot prompting strategy to generate a new CN. As a consequence of our research, we have created a high quality corpus in Spanish that includes the original HS-CN pairs translated into Spanish, in addition to the CNs generated automatically with the GPT models and that have been evaluated manually. The resulting CONAN-MT-SP corpus and its evaluation will be made available to the research community, representing the most extensive linguistic resource of CNs in Spanish to date. The results demonstrate that, although the effectiveness of GPT-4 outperforms GPT-3, both models can be used as systems to automatically generate CNs to combat the HS. Moreover, these models consistently outperform human performance in most instances.
%U https://aclanthology.org/2024.lrec-main.326
%P 3677-3688
Markdown (Informal)
[CONAN-MT-SP: A Spanish Corpus for Counternarrative Using GPT Models](https://aclanthology.org/2024.lrec-main.326) (Vallecillo Rodríguez et al., LREC-COLING 2024)
ACL
- María Estrella Vallecillo Rodríguez, Maria Victoria Cantero Romero, Isabel Cabrera De Castro, Arturo Montejo Ráez, and María Teresa Martín Valdivia. 2024. CONAN-MT-SP: A Spanish Corpus for Counternarrative Using GPT Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3677–3688, Torino, Italia. ELRA and ICCL.