@inproceedings{zeng-etal-2023-soft,
title = "Soft Language Clustering for Multilingual Model Pre-training",
author = "Zeng, Jiali and
Jiang, Yufan and
Yin, Yongjing and
Jing, Yi and
Meng, Fandong and
Lin, Binghuai and
Cao, Yunbo and
Zhou, Jie",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.388",
doi = "10.18653/v1/2023.acl-long.388",
pages = "7021--7035",
abstract = "Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typologyfrom the source language or when pre-training data is limited in size. In this paper, we propose XLM-P, a method that contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our space-efficient and model-agnostic XLM-P approach enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of XTREME, which include text classification, sequence labeling, question answering, and sentence retrieval, both base- and large-size language models pre-trained with our proposed method exhibit consistent performance improvement. Furthermore, it provides substantial advantages for low-resource languages in unsupervised sentence retrieval and for target languages that differ greatly from the source language in cross-lingual transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2023-soft">
<titleInfo>
<title>Soft Language Clustering for Multilingual Model Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiali</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjing</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Jing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binghuai</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunbo</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typologyfrom the source language or when pre-training data is limited in size. In this paper, we propose XLM-P, a method that contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our space-efficient and model-agnostic XLM-P approach enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of XTREME, which include text classification, sequence labeling, question answering, and sentence retrieval, both base- and large-size language models pre-trained with our proposed method exhibit consistent performance improvement. Furthermore, it provides substantial advantages for low-resource languages in unsupervised sentence retrieval and for target languages that differ greatly from the source language in cross-lingual transfer.</abstract>
<identifier type="citekey">zeng-etal-2023-soft</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.388</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.388</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7021</start>
<end>7035</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Soft Language Clustering for Multilingual Model Pre-training
%A Zeng, Jiali
%A Jiang, Yufan
%A Yin, Yongjing
%A Jing, Yi
%A Meng, Fandong
%A Lin, Binghuai
%A Cao, Yunbo
%A Zhou, Jie
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zeng-etal-2023-soft
%X Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typologyfrom the source language or when pre-training data is limited in size. In this paper, we propose XLM-P, a method that contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our space-efficient and model-agnostic XLM-P approach enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of XTREME, which include text classification, sequence labeling, question answering, and sentence retrieval, both base- and large-size language models pre-trained with our proposed method exhibit consistent performance improvement. Furthermore, it provides substantial advantages for low-resource languages in unsupervised sentence retrieval and for target languages that differ greatly from the source language in cross-lingual transfer.
%R 10.18653/v1/2023.acl-long.388
%U https://aclanthology.org/2023.acl-long.388
%U https://doi.org/10.18653/v1/2023.acl-long.388
%P 7021-7035
Markdown (Informal)
[Soft Language Clustering for Multilingual Model Pre-training](https://aclanthology.org/2023.acl-long.388) (Zeng et al., ACL 2023)
ACL
- Jiali Zeng, Yufan Jiang, Yongjing Yin, Yi Jing, Fandong Meng, Binghuai Lin, Yunbo Cao, and Jie Zhou. 2023. Soft Language Clustering for Multilingual Model Pre-training. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7021–7035, Toronto, Canada. Association for Computational Linguistics.