@inproceedings{lim-etal-2024-analysis,
title = "Analysis of Multi-Source Language Training in Cross-Lingual Transfer",
author = "Lim, Seonghoon and
Yun, Taejun and
Kim, Jinhyeon and
Choi, Jihun and
Kim, Taeuk",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.42",
pages = "712--725",
abstract = "The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. While cross-lingual transfer (XLT) methods have contributed to addressing this data scarcity problem, there still exists ongoing debate about the mechanisms behind their effectiveness.In this work, we focus on one of promising assumptions about inner workings of XLT, that it encourages multilingual LMs to place greater emphasis on language-agnostic or task-specific features. We test this hypothesis by examining how the patterns of XLT change with a varying number of source languages involved in the process.Our experimental findings show that the use of multiple source languages in XLT-a technique we term Multi-Source Language Training (MSLT)-leads to increased mingling of embedding spaces for different languages, supporting the claim that XLT benefits from making use of language-independent information. On the other hand, we discover that using an arbitrary combination of source languages does not always guarantee better performance. We suggest simple heuristics for identifying effective language combinations for MSLT and empirically prove its effectiveness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-etal-2024-analysis">
<titleInfo>
<title>Analysis of Multi-Source Language Training in Cross-Lingual Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seonghoon</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taejun</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinhyeon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taeuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. While cross-lingual transfer (XLT) methods have contributed to addressing this data scarcity problem, there still exists ongoing debate about the mechanisms behind their effectiveness.In this work, we focus on one of promising assumptions about inner workings of XLT, that it encourages multilingual LMs to place greater emphasis on language-agnostic or task-specific features. We test this hypothesis by examining how the patterns of XLT change with a varying number of source languages involved in the process.Our experimental findings show that the use of multiple source languages in XLT-a technique we term Multi-Source Language Training (MSLT)-leads to increased mingling of embedding spaces for different languages, supporting the claim that XLT benefits from making use of language-independent information. On the other hand, we discover that using an arbitrary combination of source languages does not always guarantee better performance. We suggest simple heuristics for identifying effective language combinations for MSLT and empirically prove its effectiveness.</abstract>
<identifier type="citekey">lim-etal-2024-analysis</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.42</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>712</start>
<end>725</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analysis of Multi-Source Language Training in Cross-Lingual Transfer
%A Lim, Seonghoon
%A Yun, Taejun
%A Kim, Jinhyeon
%A Choi, Jihun
%A Kim, Taeuk
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lim-etal-2024-analysis
%X The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. While cross-lingual transfer (XLT) methods have contributed to addressing this data scarcity problem, there still exists ongoing debate about the mechanisms behind their effectiveness.In this work, we focus on one of promising assumptions about inner workings of XLT, that it encourages multilingual LMs to place greater emphasis on language-agnostic or task-specific features. We test this hypothesis by examining how the patterns of XLT change with a varying number of source languages involved in the process.Our experimental findings show that the use of multiple source languages in XLT-a technique we term Multi-Source Language Training (MSLT)-leads to increased mingling of embedding spaces for different languages, supporting the claim that XLT benefits from making use of language-independent information. On the other hand, we discover that using an arbitrary combination of source languages does not always guarantee better performance. We suggest simple heuristics for identifying effective language combinations for MSLT and empirically prove its effectiveness.
%U https://aclanthology.org/2024.acl-long.42
%P 712-725
Markdown (Informal)
[Analysis of Multi-Source Language Training in Cross-Lingual Transfer](https://aclanthology.org/2024.acl-long.42) (Lim et al., ACL 2024)
ACL