@inproceedings{palen-michel-lignos-2023-lr,
title = "{LR}-Sum: Summarization for Less-Resourced Languages",
author = "Palen-Michel, Chester and
Lignos, Constantine",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.427",
doi = "10.18653/v1/2023.findings-acl.427",
pages = "6829--6844",
abstract = "We introduce LR-Sum, a new permissively-licensed dataset created with the goal of enabling further research in automatic summarization for less-resourced languages.LR-Sum contains human-written summaries for 40 languages, many of which are less-resourced. We describe our process for extracting and filtering the dataset from the Multilingual Open Text corpus (Palen-Michel et al., 2022).The source data is public domain newswire collected from from Voice of America websites, and LR-Sum is released under a Creative Commons license (CC BY 4.0), making it one of the most openly-licensed multilingual summarization datasets. We describe abstractive and extractive summarization experiments to establish baselines and discuss the limitations of this dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="palen-michel-lignos-2023-lr">
<titleInfo>
<title>LR-Sum: Summarization for Less-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chester</namePart>
<namePart type="family">Palen-Michel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce LR-Sum, a new permissively-licensed dataset created with the goal of enabling further research in automatic summarization for less-resourced languages.LR-Sum contains human-written summaries for 40 languages, many of which are less-resourced. We describe our process for extracting and filtering the dataset from the Multilingual Open Text corpus (Palen-Michel et al., 2022).The source data is public domain newswire collected from from Voice of America websites, and LR-Sum is released under a Creative Commons license (CC BY 4.0), making it one of the most openly-licensed multilingual summarization datasets. We describe abstractive and extractive summarization experiments to establish baselines and discuss the limitations of this dataset.</abstract>
<identifier type="citekey">palen-michel-lignos-2023-lr</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.427</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.427</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6829</start>
<end>6844</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LR-Sum: Summarization for Less-Resourced Languages
%A Palen-Michel, Chester
%A Lignos, Constantine
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F palen-michel-lignos-2023-lr
%X We introduce LR-Sum, a new permissively-licensed dataset created with the goal of enabling further research in automatic summarization for less-resourced languages.LR-Sum contains human-written summaries for 40 languages, many of which are less-resourced. We describe our process for extracting and filtering the dataset from the Multilingual Open Text corpus (Palen-Michel et al., 2022).The source data is public domain newswire collected from from Voice of America websites, and LR-Sum is released under a Creative Commons license (CC BY 4.0), making it one of the most openly-licensed multilingual summarization datasets. We describe abstractive and extractive summarization experiments to establish baselines and discuss the limitations of this dataset.
%R 10.18653/v1/2023.findings-acl.427
%U https://aclanthology.org/2023.findings-acl.427
%U https://doi.org/10.18653/v1/2023.findings-acl.427
%P 6829-6844
Markdown (Informal)
[LR-Sum: Summarization for Less-Resourced Languages](https://aclanthology.org/2023.findings-acl.427) (Palen-Michel & Lignos, Findings 2023)
ACL
- Chester Palen-Michel and Constantine Lignos. 2023. LR-Sum: Summarization for Less-Resourced Languages. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6829–6844, Toronto, Canada. Association for Computational Linguistics.