@inproceedings{inacio-etal-2024-puntuguese-corpus,
title = "Puntuguese: A Corpus of Puns in {P}ortuguese with Micro-edits",
author = "Inacio, Marcio Lima and
Wick-Pedro, Gabriela and
Ramisch, Renata and
Esp{\'\i}rito Santo, Lu{\'\i}s and
Chacon, Xiomara S. Q. and
Santos, Roney and
Sousa, Rog{\'e}rio and
Anchi{\^e}ta, Rafael and
Goncalo Oliveira, Hugo",
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.1167",
pages = "13332--13343",
abstract = "Humor is an intricate part of verbal communication and dealing with this kind of phenomenon is essential to building systems that can process language at large with all of its complexities. In this paper, we introduce Puntuguese, a new corpus of punning humor in Portuguese, motivated by previous works showing that currently available corpora for this language are still unfit for Machine Learning due to data leakage. Puntuguese comprises 4,903 manually-gathered punning one-liners in Brazilian and European Portuguese. To create negative examples that differ exclusively in terms of funniness, we carried out a micro-editing process, in which all jokes were edited by fluent Portuguese speakers to make the texts unfunny. Finally, we did some experiments on Humor Recognition, showing that Puntuguese is considerably more difficult than the previous corpus, achieving an F1-Score of 68.9{\%}. With this new dataset, we hope to enable research not only in NLP but also in other fields that are interested in studying humor; thus, the data is publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="inacio-etal-2024-puntuguese-corpus">
<titleInfo>
<title>Puntuguese: A Corpus of Puns in Portuguese with Micro-edits</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcio</namePart>
<namePart type="given">Lima</namePart>
<namePart type="family">Inacio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriela</namePart>
<namePart type="family">Wick-Pedro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Ramisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="family">Espírito Santo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiomara</namePart>
<namePart type="given">S</namePart>
<namePart type="given">Q</namePart>
<namePart type="family">Chacon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roney</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rogério</namePart>
<namePart type="family">Sousa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Anchiêta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Goncalo Oliveira</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>Humor is an intricate part of verbal communication and dealing with this kind of phenomenon is essential to building systems that can process language at large with all of its complexities. In this paper, we introduce Puntuguese, a new corpus of punning humor in Portuguese, motivated by previous works showing that currently available corpora for this language are still unfit for Machine Learning due to data leakage. Puntuguese comprises 4,903 manually-gathered punning one-liners in Brazilian and European Portuguese. To create negative examples that differ exclusively in terms of funniness, we carried out a micro-editing process, in which all jokes were edited by fluent Portuguese speakers to make the texts unfunny. Finally, we did some experiments on Humor Recognition, showing that Puntuguese is considerably more difficult than the previous corpus, achieving an F1-Score of 68.9%. With this new dataset, we hope to enable research not only in NLP but also in other fields that are interested in studying humor; thus, the data is publicly available.</abstract>
<identifier type="citekey">inacio-etal-2024-puntuguese-corpus</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1167</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13332</start>
<end>13343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Puntuguese: A Corpus of Puns in Portuguese with Micro-edits
%A Inacio, Marcio Lima
%A Wick-Pedro, Gabriela
%A Ramisch, Renata
%A Espírito Santo, Luís
%A Chacon, Xiomara S. Q.
%A Santos, Roney
%A Sousa, Rogério
%A Anchiêta, Rafael
%A Goncalo Oliveira, Hugo
%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 inacio-etal-2024-puntuguese-corpus
%X Humor is an intricate part of verbal communication and dealing with this kind of phenomenon is essential to building systems that can process language at large with all of its complexities. In this paper, we introduce Puntuguese, a new corpus of punning humor in Portuguese, motivated by previous works showing that currently available corpora for this language are still unfit for Machine Learning due to data leakage. Puntuguese comprises 4,903 manually-gathered punning one-liners in Brazilian and European Portuguese. To create negative examples that differ exclusively in terms of funniness, we carried out a micro-editing process, in which all jokes were edited by fluent Portuguese speakers to make the texts unfunny. Finally, we did some experiments on Humor Recognition, showing that Puntuguese is considerably more difficult than the previous corpus, achieving an F1-Score of 68.9%. With this new dataset, we hope to enable research not only in NLP but also in other fields that are interested in studying humor; thus, the data is publicly available.
%U https://aclanthology.org/2024.lrec-main.1167
%P 13332-13343
Markdown (Informal)
[Puntuguese: A Corpus of Puns in Portuguese with Micro-edits](https://aclanthology.org/2024.lrec-main.1167) (Inacio et al., LREC-COLING 2024)
ACL
- Marcio Lima Inacio, Gabriela Wick-Pedro, Renata Ramisch, Luís Espírito Santo, Xiomara S. Q. Chacon, Roney Santos, Rogério Sousa, Rafael Anchiêta, and Hugo Goncalo Oliveira. 2024. Puntuguese: A Corpus of Puns in Portuguese with Micro-edits. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13332–13343, Torino, Italia. ELRA and ICCL.