@inproceedings{liu-etal-2023-intemats,
title = "{I}nte{MAT}s: Integrating Granularity-Specific Multilingual Adapters for Cross-Lingual Transfer",
author = "Liu, Meizhen and
Guo, Xu and
Jiakai, He and
Chen, Jianye and
Zhou, Fengyu and
Hui, Siu",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.335",
doi = "10.18653/v1/2023.findings-emnlp.335",
pages = "5035--5049",
abstract = "Multilingual language models (MLLMs) have achieved remarkable success in various cross-lingual transfer tasks. However, they suffer poor performance in zero-shot low-resource languages, particularly when dealing with longer contexts. Existing research mainly relies on full-model fine-tuning on large parallel datasets to enhance the cross-lingual alignment of MLLMs, which is computationally expensive. In this paper, we propose InteMATs, a novel approach that integrates multilingual adapters trained on texts of different levels of granularity. To achieve this, we curate a multilingual parallel dataset comprising 42 languages to pre-train sentence-level and document-level adapters under the contrastive learning framework. Extensive experiments demonstrate the effectiveness of InteMATs in improving the cross-lingual transfer performance of MLLMs, especially on low-resource languages. Finally, our comprehensive analyses and ablation studies provide a deep understanding of the high-quality representations derived by InteMATs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-intemats">
<titleInfo>
<title>InteMATs: Integrating Granularity-Specific Multilingual Adapters for Cross-Lingual Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meizhen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Jiakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianye</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengyu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siu</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual language models (MLLMs) have achieved remarkable success in various cross-lingual transfer tasks. However, they suffer poor performance in zero-shot low-resource languages, particularly when dealing with longer contexts. Existing research mainly relies on full-model fine-tuning on large parallel datasets to enhance the cross-lingual alignment of MLLMs, which is computationally expensive. In this paper, we propose InteMATs, a novel approach that integrates multilingual adapters trained on texts of different levels of granularity. To achieve this, we curate a multilingual parallel dataset comprising 42 languages to pre-train sentence-level and document-level adapters under the contrastive learning framework. Extensive experiments demonstrate the effectiveness of InteMATs in improving the cross-lingual transfer performance of MLLMs, especially on low-resource languages. Finally, our comprehensive analyses and ablation studies provide a deep understanding of the high-quality representations derived by InteMATs.</abstract>
<identifier type="citekey">liu-etal-2023-intemats</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.335</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.335</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5035</start>
<end>5049</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InteMATs: Integrating Granularity-Specific Multilingual Adapters for Cross-Lingual Transfer
%A Liu, Meizhen
%A Guo, Xu
%A Jiakai, He
%A Chen, Jianye
%A Zhou, Fengyu
%A Hui, Siu
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F liu-etal-2023-intemats
%X Multilingual language models (MLLMs) have achieved remarkable success in various cross-lingual transfer tasks. However, they suffer poor performance in zero-shot low-resource languages, particularly when dealing with longer contexts. Existing research mainly relies on full-model fine-tuning on large parallel datasets to enhance the cross-lingual alignment of MLLMs, which is computationally expensive. In this paper, we propose InteMATs, a novel approach that integrates multilingual adapters trained on texts of different levels of granularity. To achieve this, we curate a multilingual parallel dataset comprising 42 languages to pre-train sentence-level and document-level adapters under the contrastive learning framework. Extensive experiments demonstrate the effectiveness of InteMATs in improving the cross-lingual transfer performance of MLLMs, especially on low-resource languages. Finally, our comprehensive analyses and ablation studies provide a deep understanding of the high-quality representations derived by InteMATs.
%R 10.18653/v1/2023.findings-emnlp.335
%U https://aclanthology.org/2023.findings-emnlp.335
%U https://doi.org/10.18653/v1/2023.findings-emnlp.335
%P 5035-5049
Markdown (Informal)
[InteMATs: Integrating Granularity-Specific Multilingual Adapters for Cross-Lingual Transfer](https://aclanthology.org/2023.findings-emnlp.335) (Liu et al., Findings 2023)
ACL