@inproceedings{chen-lin-2022-catamaran,
title = "{CATAMARAN}: A Cross-lingual Long Text Abstractive Summarization Dataset",
author = "Chen, Zheng and
Lin, Hongyu",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.749",
pages = "6932--6937",
abstract = "Cross-lingual summarization, which produces the summary in one language from a given source document in another language, could be extremely helpful for humans to obtain information across the world. However, it is still a little-explored task due to the lack of datasets. Recent studies are primarily based on pseudo-cross-lingual datasets obtained by translation. Such an approach would inevitably lead to the loss of information in the original document and introduce noise into the summary, thus hurting the overall performance. In this paper, we present CATAMARAN, the first high-quality cross-lingual long text abstractive summarization dataset. It contains about 20,000 parallel news articles and corresponding summaries, all written by humans. The average lengths of articles are 1133.65 for English articles and 2035.33 for Chinese articles, and the average lengths of the summaries are 26.59 and 70.05, respectively. We train and evaluate an mBART-based cross-lingual abstractive summarization model using our dataset. The result shows that, compared with mono-lingual systems, the cross-lingual abstractive summarization system could also achieve solid performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-lin-2022-catamaran">
<titleInfo>
<title>CATAMARAN: A Cross-lingual Long Text Abstractive Summarization Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual summarization, which produces the summary in one language from a given source document in another language, could be extremely helpful for humans to obtain information across the world. However, it is still a little-explored task due to the lack of datasets. Recent studies are primarily based on pseudo-cross-lingual datasets obtained by translation. Such an approach would inevitably lead to the loss of information in the original document and introduce noise into the summary, thus hurting the overall performance. In this paper, we present CATAMARAN, the first high-quality cross-lingual long text abstractive summarization dataset. It contains about 20,000 parallel news articles and corresponding summaries, all written by humans. The average lengths of articles are 1133.65 for English articles and 2035.33 for Chinese articles, and the average lengths of the summaries are 26.59 and 70.05, respectively. We train and evaluate an mBART-based cross-lingual abstractive summarization model using our dataset. The result shows that, compared with mono-lingual systems, the cross-lingual abstractive summarization system could also achieve solid performance.</abstract>
<identifier type="citekey">chen-lin-2022-catamaran</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.749</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6932</start>
<end>6937</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CATAMARAN: A Cross-lingual Long Text Abstractive Summarization Dataset
%A Chen, Zheng
%A Lin, Hongyu
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F chen-lin-2022-catamaran
%X Cross-lingual summarization, which produces the summary in one language from a given source document in another language, could be extremely helpful for humans to obtain information across the world. However, it is still a little-explored task due to the lack of datasets. Recent studies are primarily based on pseudo-cross-lingual datasets obtained by translation. Such an approach would inevitably lead to the loss of information in the original document and introduce noise into the summary, thus hurting the overall performance. In this paper, we present CATAMARAN, the first high-quality cross-lingual long text abstractive summarization dataset. It contains about 20,000 parallel news articles and corresponding summaries, all written by humans. The average lengths of articles are 1133.65 for English articles and 2035.33 for Chinese articles, and the average lengths of the summaries are 26.59 and 70.05, respectively. We train and evaluate an mBART-based cross-lingual abstractive summarization model using our dataset. The result shows that, compared with mono-lingual systems, the cross-lingual abstractive summarization system could also achieve solid performance.
%U https://aclanthology.org/2022.lrec-1.749
%P 6932-6937
Markdown (Informal)
[CATAMARAN: A Cross-lingual Long Text Abstractive Summarization Dataset](https://aclanthology.org/2022.lrec-1.749) (Chen & Lin, LREC 2022)
ACL