@inproceedings{calizzano-etal-2022-generating,
title = "Generating Extended and Multilingual Summaries with Pre-trained Transformers",
author = "Calizzano, R{\'e}mi and
Ostendorff, Malte and
Ruan, Qian and
Rehm, Georg",
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-1.175",
pages = "1640--1650",
abstract = "Almost all summarisation methods and datasets focus on a single language and short summaries. We introduce a new dataset called WikinewsSum for English, German, French, Spanish, Portuguese, Polish, and Italian summarisation tailored for extended summaries of approx. 11 sentences. The dataset comprises 39,626 summaries which are news articles from Wikinews and their sources. We compare three multilingual transformer models on the extractive summarisation task and three training scenarios on which we fine-tune mT5 to perform abstractive summarisation. This results in strong baselines for both extractive and abstractive summarisation on WikinewsSum. We also show how the combination of an extractive model with an abstractive one can be used to create extended abstractive summaries from long input documents. Finally, our results show that fine-tuning mT5 on all the languages combined significantly improves the summarisation performance on low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="calizzano-etal-2022-generating">
<titleInfo>
<title>Generating Extended and Multilingual Summaries with Pre-trained Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Calizzano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Ostendorff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</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>Almost all summarisation methods and datasets focus on a single language and short summaries. We introduce a new dataset called WikinewsSum for English, German, French, Spanish, Portuguese, Polish, and Italian summarisation tailored for extended summaries of approx. 11 sentences. The dataset comprises 39,626 summaries which are news articles from Wikinews and their sources. We compare three multilingual transformer models on the extractive summarisation task and three training scenarios on which we fine-tune mT5 to perform abstractive summarisation. This results in strong baselines for both extractive and abstractive summarisation on WikinewsSum. We also show how the combination of an extractive model with an abstractive one can be used to create extended abstractive summaries from long input documents. Finally, our results show that fine-tuning mT5 on all the languages combined significantly improves the summarisation performance on low-resource languages.</abstract>
<identifier type="citekey">calizzano-etal-2022-generating</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.175</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1640</start>
<end>1650</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Extended and Multilingual Summaries with Pre-trained Transformers
%A Calizzano, Rémi
%A Ostendorff, Malte
%A Ruan, Qian
%A Rehm, Georg
%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 calizzano-etal-2022-generating
%X Almost all summarisation methods and datasets focus on a single language and short summaries. We introduce a new dataset called WikinewsSum for English, German, French, Spanish, Portuguese, Polish, and Italian summarisation tailored for extended summaries of approx. 11 sentences. The dataset comprises 39,626 summaries which are news articles from Wikinews and their sources. We compare three multilingual transformer models on the extractive summarisation task and three training scenarios on which we fine-tune mT5 to perform abstractive summarisation. This results in strong baselines for both extractive and abstractive summarisation on WikinewsSum. We also show how the combination of an extractive model with an abstractive one can be used to create extended abstractive summaries from long input documents. Finally, our results show that fine-tuning mT5 on all the languages combined significantly improves the summarisation performance on low-resource languages.
%U https://aclanthology.org/2022.lrec-1.175
%P 1640-1650
Markdown (Informal)
[Generating Extended and Multilingual Summaries with Pre-trained Transformers](https://aclanthology.org/2022.lrec-1.175) (Calizzano et al., LREC 2022)
ACL