@inproceedings{jundi-lapesa-2022-translate,
title = "How to Translate Your Samples and Choose Your Shots? Analyzing Translate-train {\&} Few-shot Cross-lingual Transfer",
author = "Jundi, Iman and
Lapesa, Gabriella",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.11",
doi = "10.18653/v1/2022.findings-naacl.11",
pages = "129--150",
abstract = "Translate-train or few-shot cross-lingual transfer can be used to improve the zero-shot performance of multilingual pretrained language models. Few-shot utilizes high-quality low-quantity samples (often manually translated from the English corpus ). Translate-train employs a machine translation of the English corpus, resulting in samples with lower quality that could be scaled to high quantity. Given the lower cost and higher availability of machine translation compared to manual professional translation, it is important to systematically compare few-shot and translate-train, understand when each has an advantage, and investigate how to choose the shots to translate in order to increase the few-shot gain. This work aims to fill this gap: we compare and quantify the performance gain of few-shot vs. translate-train using three different base models and a varying number of samples for three tasks/datasets (XNLI, PAWS-X, XQuAD) spanning 17 languages. We show that scaling up the training data using machine translation gives a larger gain compared to using the small-scale (higher-quality) few-shot data. When few-shot is beneficial, we show that there are random sets of samples that perform better across languages and that the performance on English and on the machine-translation of the samples can both be used to choose the shots to manually translate for an increased few-shot gain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jundi-lapesa-2022-translate">
<titleInfo>
<title>How to Translate Your Samples and Choose Your Shots? Analyzing Translate-train & Few-shot Cross-lingual Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iman</namePart>
<namePart type="family">Jundi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</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>Findings of the Association for Computational Linguistics: NAACL 2022</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>Translate-train or few-shot cross-lingual transfer can be used to improve the zero-shot performance of multilingual pretrained language models. Few-shot utilizes high-quality low-quantity samples (often manually translated from the English corpus ). Translate-train employs a machine translation of the English corpus, resulting in samples with lower quality that could be scaled to high quantity. Given the lower cost and higher availability of machine translation compared to manual professional translation, it is important to systematically compare few-shot and translate-train, understand when each has an advantage, and investigate how to choose the shots to translate in order to increase the few-shot gain. This work aims to fill this gap: we compare and quantify the performance gain of few-shot vs. translate-train using three different base models and a varying number of samples for three tasks/datasets (XNLI, PAWS-X, XQuAD) spanning 17 languages. We show that scaling up the training data using machine translation gives a larger gain compared to using the small-scale (higher-quality) few-shot data. When few-shot is beneficial, we show that there are random sets of samples that perform better across languages and that the performance on English and on the machine-translation of the samples can both be used to choose the shots to manually translate for an increased few-shot gain.</abstract>
<identifier type="citekey">jundi-lapesa-2022-translate</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.11</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.11</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>129</start>
<end>150</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Translate Your Samples and Choose Your Shots? Analyzing Translate-train & Few-shot Cross-lingual Transfer
%A Jundi, Iman
%A Lapesa, Gabriella
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F jundi-lapesa-2022-translate
%X Translate-train or few-shot cross-lingual transfer can be used to improve the zero-shot performance of multilingual pretrained language models. Few-shot utilizes high-quality low-quantity samples (often manually translated from the English corpus ). Translate-train employs a machine translation of the English corpus, resulting in samples with lower quality that could be scaled to high quantity. Given the lower cost and higher availability of machine translation compared to manual professional translation, it is important to systematically compare few-shot and translate-train, understand when each has an advantage, and investigate how to choose the shots to translate in order to increase the few-shot gain. This work aims to fill this gap: we compare and quantify the performance gain of few-shot vs. translate-train using three different base models and a varying number of samples for three tasks/datasets (XNLI, PAWS-X, XQuAD) spanning 17 languages. We show that scaling up the training data using machine translation gives a larger gain compared to using the small-scale (higher-quality) few-shot data. When few-shot is beneficial, we show that there are random sets of samples that perform better across languages and that the performance on English and on the machine-translation of the samples can both be used to choose the shots to manually translate for an increased few-shot gain.
%R 10.18653/v1/2022.findings-naacl.11
%U https://aclanthology.org/2022.findings-naacl.11
%U https://doi.org/10.18653/v1/2022.findings-naacl.11
%P 129-150
Markdown (Informal)
[How to Translate Your Samples and Choose Your Shots? Analyzing Translate-train & Few-shot Cross-lingual Transfer](https://aclanthology.org/2022.findings-naacl.11) (Jundi & Lapesa, Findings 2022)
ACL