@inproceedings{reid-artetxe-2022-paradise,
title = "{PARADISE}: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining",
author = "Reid, Machel and
Artetxe, Mikel",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.58",
doi = "10.18653/v1/2022.naacl-main.58",
pages = "800--810",
abstract = "Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora and do not make use of the strong cross-lingual signal contained in parallel data. In this paper, we present PARADISE (PARAllel {\&}Denoising Integration in SEquence-to-sequence models), which extends the conventional denoising objective used to train these models by (i) replacing words in the noised sequence according to a multilingual dictionary, and (ii) predicting the reference translation according to a parallel corpus instead of recovering the original sequence. Our experiments on machine translation and cross-lingual natural language inference show an average improvement of 2.0 BLEU points and 6.7 accuracy points from integrating parallel data into pretraining, respectively, obtaining results that are competitive with several popular models at a fraction of their computational cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reid-artetxe-2022-paradise">
<titleInfo>
<title>PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Machel</namePart>
<namePart type="family">Reid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Artetxe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora and do not make use of the strong cross-lingual signal contained in parallel data. In this paper, we present PARADISE (PARAllel &Denoising Integration in SEquence-to-sequence models), which extends the conventional denoising objective used to train these models by (i) replacing words in the noised sequence according to a multilingual dictionary, and (ii) predicting the reference translation according to a parallel corpus instead of recovering the original sequence. Our experiments on machine translation and cross-lingual natural language inference show an average improvement of 2.0 BLEU points and 6.7 accuracy points from integrating parallel data into pretraining, respectively, obtaining results that are competitive with several popular models at a fraction of their computational cost.</abstract>
<identifier type="citekey">reid-artetxe-2022-paradise</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.58</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.58</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>800</start>
<end>810</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining
%A Reid, Machel
%A Artetxe, Mikel
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F reid-artetxe-2022-paradise
%X Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora and do not make use of the strong cross-lingual signal contained in parallel data. In this paper, we present PARADISE (PARAllel &Denoising Integration in SEquence-to-sequence models), which extends the conventional denoising objective used to train these models by (i) replacing words in the noised sequence according to a multilingual dictionary, and (ii) predicting the reference translation according to a parallel corpus instead of recovering the original sequence. Our experiments on machine translation and cross-lingual natural language inference show an average improvement of 2.0 BLEU points and 6.7 accuracy points from integrating parallel data into pretraining, respectively, obtaining results that are competitive with several popular models at a fraction of their computational cost.
%R 10.18653/v1/2022.naacl-main.58
%U https://aclanthology.org/2022.naacl-main.58
%U https://doi.org/10.18653/v1/2022.naacl-main.58
%P 800-810
Markdown (Informal)
[PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining](https://aclanthology.org/2022.naacl-main.58) (Reid & Artetxe, NAACL 2022)
ACL