@inproceedings{ebing-glavas-2024-translate,
title = "To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages",
author = "Ebing, Benedikt and
Glava{\v{s}}, Goran",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.298",
pages = "5325--5344",
abstract = "Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent advances in massively multilingual MT, in this work, we systematically evaluate existing and propose new translation-based XLT approaches for transfer to low-resource languages. We show that all translation-based approaches dramatically outperform zero-shot XLT with mLMs{---}with the combination of round-trip translation of the source-language training data and the translation of the target-language test instances at inference{---}being generally the most effective. We next show that one can obtain further empirical gains by adding reliable translations to other high-resource languages to the training data. Moreover, we propose an effective translation-based XLT strategy even for languages not supported by the MT system. Finally, we show that model selection for XLT based on target-language validation data obtained with MT outperforms model selection based on the source-language data. We believe our findings warrant a broader inclusion of more robust translation-based baselines in XLT research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ebing-glavas-2024-translate">
<titleInfo>
<title>To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benedikt</namePart>
<namePart type="family">Ebing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent advances in massively multilingual MT, in this work, we systematically evaluate existing and propose new translation-based XLT approaches for transfer to low-resource languages. We show that all translation-based approaches dramatically outperform zero-shot XLT with mLMs—with the combination of round-trip translation of the source-language training data and the translation of the target-language test instances at inference—being generally the most effective. We next show that one can obtain further empirical gains by adding reliable translations to other high-resource languages to the training data. Moreover, we propose an effective translation-based XLT strategy even for languages not supported by the MT system. Finally, we show that model selection for XLT based on target-language validation data obtained with MT outperforms model selection based on the source-language data. We believe our findings warrant a broader inclusion of more robust translation-based baselines in XLT research.</abstract>
<identifier type="citekey">ebing-glavas-2024-translate</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.298</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>5325</start>
<end>5344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages
%A Ebing, Benedikt
%A Glavaš, Goran
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F ebing-glavas-2024-translate
%X Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent advances in massively multilingual MT, in this work, we systematically evaluate existing and propose new translation-based XLT approaches for transfer to low-resource languages. We show that all translation-based approaches dramatically outperform zero-shot XLT with mLMs—with the combination of round-trip translation of the source-language training data and the translation of the target-language test instances at inference—being generally the most effective. We next show that one can obtain further empirical gains by adding reliable translations to other high-resource languages to the training data. Moreover, we propose an effective translation-based XLT strategy even for languages not supported by the MT system. Finally, we show that model selection for XLT based on target-language validation data obtained with MT outperforms model selection based on the source-language data. We believe our findings warrant a broader inclusion of more robust translation-based baselines in XLT research.
%U https://aclanthology.org/2024.naacl-long.298
%P 5325-5344
Markdown (Informal)
[To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages](https://aclanthology.org/2024.naacl-long.298) (Ebing & Glavaš, NAACL 2024)
ACL