@inproceedings{fan-etal-2021-discovering-representation,
title = "Discovering Representation Sprachbund For Multilingual Pre-Training",
author = "Fan, Yimin and
Liang, Yaobo and
Muzio, Alexandre and
Hassan, Hany and
Li, Houqiang and
Zhou, Ming and
Duan, Nan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.75/",
doi = "10.18653/v1/2021.findings-emnlp.75",
pages = "881--894",
abstract = "Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low-resource ones. However, due to significant typological differences and contradictions between some languages, such models usually perform poorly on many languages and cross-lingual settings, which shows the difficulty of learning a single model to handle massive diverse languages well at the same time. To alleviate this issue, we present a new multilingual pre-training pipeline. We propose to generate language representation from multilingual pre-trained model and conduct linguistic analysis to show that language representation similarity reflects linguistic similarity from multiple perspectives, including language family, geographical sprachbund, lexicostatistics, and syntax. Then we cluster all the target languages into multiple groups and name each group as a representation sprachbund. Thus, languages in the same representation sprachbund are supposed to boost each other in both pre-training and fine-tuning as they share rich linguistic similarity. We pre-train one multilingual model for each representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2021-discovering-representation">
<titleInfo>
<title>Discovering Representation Sprachbund For Multilingual Pre-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimin</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaobo</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Muzio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hany</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houqiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low-resource ones. However, due to significant typological differences and contradictions between some languages, such models usually perform poorly on many languages and cross-lingual settings, which shows the difficulty of learning a single model to handle massive diverse languages well at the same time. To alleviate this issue, we present a new multilingual pre-training pipeline. We propose to generate language representation from multilingual pre-trained model and conduct linguistic analysis to show that language representation similarity reflects linguistic similarity from multiple perspectives, including language family, geographical sprachbund, lexicostatistics, and syntax. Then we cluster all the target languages into multiple groups and name each group as a representation sprachbund. Thus, languages in the same representation sprachbund are supposed to boost each other in both pre-training and fine-tuning as they share rich linguistic similarity. We pre-train one multilingual model for each representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.</abstract>
<identifier type="citekey">fan-etal-2021-discovering-representation</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.75</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.75/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>881</start>
<end>894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discovering Representation Sprachbund For Multilingual Pre-Training
%A Fan, Yimin
%A Liang, Yaobo
%A Muzio, Alexandre
%A Hassan, Hany
%A Li, Houqiang
%A Zhou, Ming
%A Duan, Nan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F fan-etal-2021-discovering-representation
%X Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low-resource ones. However, due to significant typological differences and contradictions between some languages, such models usually perform poorly on many languages and cross-lingual settings, which shows the difficulty of learning a single model to handle massive diverse languages well at the same time. To alleviate this issue, we present a new multilingual pre-training pipeline. We propose to generate language representation from multilingual pre-trained model and conduct linguistic analysis to show that language representation similarity reflects linguistic similarity from multiple perspectives, including language family, geographical sprachbund, lexicostatistics, and syntax. Then we cluster all the target languages into multiple groups and name each group as a representation sprachbund. Thus, languages in the same representation sprachbund are supposed to boost each other in both pre-training and fine-tuning as they share rich linguistic similarity. We pre-train one multilingual model for each representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
%R 10.18653/v1/2021.findings-emnlp.75
%U https://aclanthology.org/2021.findings-emnlp.75/
%U https://doi.org/10.18653/v1/2021.findings-emnlp.75
%P 881-894
Markdown (Informal)
[Discovering Representation Sprachbund For Multilingual Pre-Training](https://aclanthology.org/2021.findings-emnlp.75/) (Fan et al., Findings 2021)
ACL