@inproceedings{fujinuma-etal-2022-match,
title = "Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability",
author = "Fujinuma, Yoshinari and
Boyd-Graber, Jordan and
Kann, Katharina",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.106/",
doi = "10.18653/v1/2022.acl-long.106",
pages = "1500--1512",
abstract = "Pretrained multilingual models enable zero-shot learning even for unseen languages, and that performance can be further improved via adaptation prior to finetuning. However, it is unclear how the number of pretraining languages influences a model`s zero-shot learning for languages unseen during pretraining. To fill this gap, we ask the following research questions: (1) How does the number of pretraining languages influence zero-shot performance on unseen target languages? (2) Does the answer to that question change with model adaptation? (3) Do the findings for our first question change if the languages used for pretraining are all related? Our experiments on pretraining with related languages indicate that choosing a diverse set of languages is crucial. Without model adaptation, surprisingly, increasing the number of pretraining languages yields better results up to adding related languages, after which performance plateaus. In contrast, with model adaptation via continued pretraining, pretraining on a larger number of languages often gives further improvement, suggesting that model adaptation is crucial to exploit additional pretraining languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fujinuma-etal-2022-match">
<titleInfo>
<title>Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoshinari</namePart>
<namePart type="family">Fujinuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretrained multilingual models enable zero-shot learning even for unseen languages, and that performance can be further improved via adaptation prior to finetuning. However, it is unclear how the number of pretraining languages influences a model‘s zero-shot learning for languages unseen during pretraining. To fill this gap, we ask the following research questions: (1) How does the number of pretraining languages influence zero-shot performance on unseen target languages? (2) Does the answer to that question change with model adaptation? (3) Do the findings for our first question change if the languages used for pretraining are all related? Our experiments on pretraining with related languages indicate that choosing a diverse set of languages is crucial. Without model adaptation, surprisingly, increasing the number of pretraining languages yields better results up to adding related languages, after which performance plateaus. In contrast, with model adaptation via continued pretraining, pretraining on a larger number of languages often gives further improvement, suggesting that model adaptation is crucial to exploit additional pretraining languages.</abstract>
<identifier type="citekey">fujinuma-etal-2022-match</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.106</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.106/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1500</start>
<end>1512</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
%A Fujinuma, Yoshinari
%A Boyd-Graber, Jordan
%A Kann, Katharina
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F fujinuma-etal-2022-match
%X Pretrained multilingual models enable zero-shot learning even for unseen languages, and that performance can be further improved via adaptation prior to finetuning. However, it is unclear how the number of pretraining languages influences a model‘s zero-shot learning for languages unseen during pretraining. To fill this gap, we ask the following research questions: (1) How does the number of pretraining languages influence zero-shot performance on unseen target languages? (2) Does the answer to that question change with model adaptation? (3) Do the findings for our first question change if the languages used for pretraining are all related? Our experiments on pretraining with related languages indicate that choosing a diverse set of languages is crucial. Without model adaptation, surprisingly, increasing the number of pretraining languages yields better results up to adding related languages, after which performance plateaus. In contrast, with model adaptation via continued pretraining, pretraining on a larger number of languages often gives further improvement, suggesting that model adaptation is crucial to exploit additional pretraining languages.
%R 10.18653/v1/2022.acl-long.106
%U https://aclanthology.org/2022.acl-long.106/
%U https://doi.org/10.18653/v1/2022.acl-long.106
%P 1500-1512
Markdown (Informal)
[Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability](https://aclanthology.org/2022.acl-long.106/) (Fujinuma et al., ACL 2022)
ACL