@inproceedings{dimas-furtado-etal-2024-dore-dataset,
title = "{DORE}: A Dataset for {P}ortuguese Definition Generation",
author = "Dimas Furtado, Anna Beatriz and
Ranasinghe, Tharindu and
Blain, Frederic and
Mitkov, Ruslan",
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.473",
pages = "5315--5322",
abstract = "Definition modelling (DM) is the task of automatically generating a dictionary definition of a specific word. Computational systems that are capable of DM can have numerous applications benefiting a wide range of audiences. As DM is considered a supervised natural language generation problem, these systems require large annotated datasets to train the machine learning (ML) models. Several DM datasets have been released for English and other high-resource languages. While Portuguese is considered a mid/high-resource language in most natural language processing tasks and is spoken by more than 200 million native speakers, there is no DM dataset available for Portuguese. In this research, we fill this gap by introducing DORE; the first dataset for \textbf{D}efinition M\textbf{O}delling for Po\textbf{R}tugu\textbf{E}se containing more than 100,000 definitions. We also evaluate several deep learning based DM models on DORE and report the results. The dataset and the findings of this paper will facilitate research and study of Portuguese in wider contexts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dimas-furtado-etal-2024-dore-dataset">
<titleInfo>
<title>DORE: A Dataset for Portuguese Definition Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="given">Beatriz</namePart>
<namePart type="family">Dimas Furtado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</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>Definition modelling (DM) is the task of automatically generating a dictionary definition of a specific word. Computational systems that are capable of DM can have numerous applications benefiting a wide range of audiences. As DM is considered a supervised natural language generation problem, these systems require large annotated datasets to train the machine learning (ML) models. Several DM datasets have been released for English and other high-resource languages. While Portuguese is considered a mid/high-resource language in most natural language processing tasks and is spoken by more than 200 million native speakers, there is no DM dataset available for Portuguese. In this research, we fill this gap by introducing DORE; the first dataset for Definition MOdelling for PoRtuguEse containing more than 100,000 definitions. We also evaluate several deep learning based DM models on DORE and report the results. The dataset and the findings of this paper will facilitate research and study of Portuguese in wider contexts.</abstract>
<identifier type="citekey">dimas-furtado-etal-2024-dore-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.473</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5315</start>
<end>5322</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DORE: A Dataset for Portuguese Definition Generation
%A Dimas Furtado, Anna Beatriz
%A Ranasinghe, Tharindu
%A Blain, Frederic
%A Mitkov, Ruslan
%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 dimas-furtado-etal-2024-dore-dataset
%X Definition modelling (DM) is the task of automatically generating a dictionary definition of a specific word. Computational systems that are capable of DM can have numerous applications benefiting a wide range of audiences. As DM is considered a supervised natural language generation problem, these systems require large annotated datasets to train the machine learning (ML) models. Several DM datasets have been released for English and other high-resource languages. While Portuguese is considered a mid/high-resource language in most natural language processing tasks and is spoken by more than 200 million native speakers, there is no DM dataset available for Portuguese. In this research, we fill this gap by introducing DORE; the first dataset for Definition MOdelling for PoRtuguEse containing more than 100,000 definitions. We also evaluate several deep learning based DM models on DORE and report the results. The dataset and the findings of this paper will facilitate research and study of Portuguese in wider contexts.
%U https://aclanthology.org/2024.lrec-main.473
%P 5315-5322
Markdown (Informal)
[DORE: A Dataset for Portuguese Definition Generation](https://aclanthology.org/2024.lrec-main.473) (Dimas Furtado et al., LREC-COLING 2024)
ACL
- Anna Beatriz Dimas Furtado, Tharindu Ranasinghe, Frederic Blain, and Ruslan Mitkov. 2024. DORE: A Dataset for Portuguese Definition Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5315–5322, Torino, Italia. ELRA and ICCL.