@inproceedings{korotkova-etal-2024-multilinguality,
title = "Multilinguality or Back-translation? A Case Study with {E}stonian",
author = "Korotkova, Elizaveta and
Purason, Taido and
Luhtaru, Agnes and
Fishel, Mark",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1033",
pages = "11838--11848",
abstract = "Machine translation quality is highly reliant on large amounts of training data, and, when a limited amount of parallel data is available, synthetic back-translated or multilingual data can be used in addition. In this work, we introduce SynEst, a synthetic corpus of translations from 11 languages into Estonian which totals over 1 billion sentence pairs. Using this corpus, we investigate whether adding synthetic or English-centric additional data yields better translation quality for translation directions that do not include English. Our results show that while both strategies are effective, synthetic data gives better results. Our final models improve the performance of the baseline No Language Left Behind model while retaining its source-side multilinguality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="korotkova-etal-2024-multilinguality">
<titleInfo>
<title>Multilinguality or Back-translation? A Case Study with Estonian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizaveta</namePart>
<namePart type="family">Korotkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taido</namePart>
<namePart type="family">Purason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnes</namePart>
<namePart type="family">Luhtaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation quality is highly reliant on large amounts of training data, and, when a limited amount of parallel data is available, synthetic back-translated or multilingual data can be used in addition. In this work, we introduce SynEst, a synthetic corpus of translations from 11 languages into Estonian which totals over 1 billion sentence pairs. Using this corpus, we investigate whether adding synthetic or English-centric additional data yields better translation quality for translation directions that do not include English. Our results show that while both strategies are effective, synthetic data gives better results. Our final models improve the performance of the baseline No Language Left Behind model while retaining its source-side multilinguality.</abstract>
<identifier type="citekey">korotkova-etal-2024-multilinguality</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1033</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11838</start>
<end>11848</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilinguality or Back-translation? A Case Study with Estonian
%A Korotkova, Elizaveta
%A Purason, Taido
%A Luhtaru, Agnes
%A Fishel, Mark
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F korotkova-etal-2024-multilinguality
%X Machine translation quality is highly reliant on large amounts of training data, and, when a limited amount of parallel data is available, synthetic back-translated or multilingual data can be used in addition. In this work, we introduce SynEst, a synthetic corpus of translations from 11 languages into Estonian which totals over 1 billion sentence pairs. Using this corpus, we investigate whether adding synthetic or English-centric additional data yields better translation quality for translation directions that do not include English. Our results show that while both strategies are effective, synthetic data gives better results. Our final models improve the performance of the baseline No Language Left Behind model while retaining its source-side multilinguality.
%U https://aclanthology.org/2024.lrec-main.1033
%P 11838-11848
Markdown (Informal)
[Multilinguality or Back-translation? A Case Study with Estonian](https://aclanthology.org/2024.lrec-main.1033) (Korotkova et al., LREC-COLING 2024)
ACL
- Elizaveta Korotkova, Taido Purason, Agnes Luhtaru, and Mark Fishel. 2024. Multilinguality or Back-translation? A Case Study with Estonian. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11838–11848, Torino, Italia. ELRA and ICCL.