@inproceedings{do-etal-2024-contrastivemix,
title = "{C}ontrastive{M}ix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval",
author = "Do, Junggeun and
Lee, Jaeseong and
Hwang, Seung-won",
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 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.17",
doi = "10.18653/v1/2024.naacl-short.17",
pages = "197--204",
abstract = "Multilingual pretrained language models (mPLMs) have been widely adopted in cross-lingual transfer, and code-mixing has demonstrated effectiveness across various tasks in the absence of target language data. Our contribution involves an in-depth investigation into the counterproductive nature of training mPLMs on code-mixed data for information retrieval (IR). Our finding is that while code-mixing demonstrates a positive effect in aligning representations across languages, it hampers the IR-specific objective of matching representations between queries and relevant passages. To balance between positive and negative effects, we introduce ContrastiveMix, which disentangles contrastive loss between these conflicting objectives, thereby enhancing zero-shot IR performance. Specifically, we leverage both English and code-mixed data and employ two contrastive loss functions, by adding an additional contrastive loss that aligns embeddings of English data with their code-mixed counterparts in the query encoder. Our proposed ContrastiveMix exhibits statistically significant outperformance compared to mDPR, particularly in scenarios involving lower linguistic similarity, where the conflict between goals is more pronounced.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-etal-2024-contrastivemix">
<titleInfo>
<title>ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junggeun</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeseong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</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 2: Short 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>Multilingual pretrained language models (mPLMs) have been widely adopted in cross-lingual transfer, and code-mixing has demonstrated effectiveness across various tasks in the absence of target language data. Our contribution involves an in-depth investigation into the counterproductive nature of training mPLMs on code-mixed data for information retrieval (IR). Our finding is that while code-mixing demonstrates a positive effect in aligning representations across languages, it hampers the IR-specific objective of matching representations between queries and relevant passages. To balance between positive and negative effects, we introduce ContrastiveMix, which disentangles contrastive loss between these conflicting objectives, thereby enhancing zero-shot IR performance. Specifically, we leverage both English and code-mixed data and employ two contrastive loss functions, by adding an additional contrastive loss that aligns embeddings of English data with their code-mixed counterparts in the query encoder. Our proposed ContrastiveMix exhibits statistically significant outperformance compared to mDPR, particularly in scenarios involving lower linguistic similarity, where the conflict between goals is more pronounced.</abstract>
<identifier type="citekey">do-etal-2024-contrastivemix</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-short.17</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.17</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>197</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval
%A Do, Junggeun
%A Lee, Jaeseong
%A Hwang, Seung-won
%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 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F do-etal-2024-contrastivemix
%X Multilingual pretrained language models (mPLMs) have been widely adopted in cross-lingual transfer, and code-mixing has demonstrated effectiveness across various tasks in the absence of target language data. Our contribution involves an in-depth investigation into the counterproductive nature of training mPLMs on code-mixed data for information retrieval (IR). Our finding is that while code-mixing demonstrates a positive effect in aligning representations across languages, it hampers the IR-specific objective of matching representations between queries and relevant passages. To balance between positive and negative effects, we introduce ContrastiveMix, which disentangles contrastive loss between these conflicting objectives, thereby enhancing zero-shot IR performance. Specifically, we leverage both English and code-mixed data and employ two contrastive loss functions, by adding an additional contrastive loss that aligns embeddings of English data with their code-mixed counterparts in the query encoder. Our proposed ContrastiveMix exhibits statistically significant outperformance compared to mDPR, particularly in scenarios involving lower linguistic similarity, where the conflict between goals is more pronounced.
%R 10.18653/v1/2024.naacl-short.17
%U https://aclanthology.org/2024.naacl-short.17
%U https://doi.org/10.18653/v1/2024.naacl-short.17
%P 197-204
Markdown (Informal)
[ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval](https://aclanthology.org/2024.naacl-short.17) (Do et al., NAACL 2024)
ACL