@inproceedings{martinc-etal-2022-effectiveness,
title = "Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings",
author = "Martinc, Matej and
Montariol, Syrielle and
Pivovarova, Lidia and
Zosa, Elaine",
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-1.381",
pages = "3561--3570",
abstract = "We tackle the problem of neural headline generation in a low-resource setting, where only limited amount of data is available to train a model. We compare the ideal high-resource scenario on English with results obtained on a smaller subset of the same data and also run experiments on two small news corpora covering low-resource languages, Croatian and Estonian. Two options for headline generation in a multilingual low-resource scenario are investigated: a pretrained multilingual encoder-decoder model and a combination of two pretrained language models, one used as an encoder and the other as a decoder, connected with a cross-attention layer that needs to be trained from scratch. The results show that the first approach outperforms the second one by a large margin. We explore several data augmentation and pretraining strategies in order to improve the performance of both models and show that while we can drastically improve the second approach using these strategies, they have little to no effect on the performance of the pretrained encoder-decoder model. Finally, we propose two new measures for evaluating the performance of the models besides the classic ROUGE scores.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinc-etal-2022-effectiveness">
<titleInfo>
<title>Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matej</namePart>
<namePart type="family">Martinc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaine</namePart>
<namePart type="family">Zosa</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>We tackle the problem of neural headline generation in a low-resource setting, where only limited amount of data is available to train a model. We compare the ideal high-resource scenario on English with results obtained on a smaller subset of the same data and also run experiments on two small news corpora covering low-resource languages, Croatian and Estonian. Two options for headline generation in a multilingual low-resource scenario are investigated: a pretrained multilingual encoder-decoder model and a combination of two pretrained language models, one used as an encoder and the other as a decoder, connected with a cross-attention layer that needs to be trained from scratch. The results show that the first approach outperforms the second one by a large margin. We explore several data augmentation and pretraining strategies in order to improve the performance of both models and show that while we can drastically improve the second approach using these strategies, they have little to no effect on the performance of the pretrained encoder-decoder model. Finally, we propose two new measures for evaluating the performance of the models besides the classic ROUGE scores.</abstract>
<identifier type="citekey">martinc-etal-2022-effectiveness</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.381</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3561</start>
<end>3570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings
%A Martinc, Matej
%A Montariol, Syrielle
%A Pivovarova, Lidia
%A Zosa, Elaine
%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 martinc-etal-2022-effectiveness
%X We tackle the problem of neural headline generation in a low-resource setting, where only limited amount of data is available to train a model. We compare the ideal high-resource scenario on English with results obtained on a smaller subset of the same data and also run experiments on two small news corpora covering low-resource languages, Croatian and Estonian. Two options for headline generation in a multilingual low-resource scenario are investigated: a pretrained multilingual encoder-decoder model and a combination of two pretrained language models, one used as an encoder and the other as a decoder, connected with a cross-attention layer that needs to be trained from scratch. The results show that the first approach outperforms the second one by a large margin. We explore several data augmentation and pretraining strategies in order to improve the performance of both models and show that while we can drastically improve the second approach using these strategies, they have little to no effect on the performance of the pretrained encoder-decoder model. Finally, we propose two new measures for evaluating the performance of the models besides the classic ROUGE scores.
%U https://aclanthology.org/2022.lrec-1.381
%P 3561-3570
Markdown (Informal)
[Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings](https://aclanthology.org/2022.lrec-1.381) (Martinc et al., LREC 2022)
ACL