@inproceedings{yang-etal-2021-bilingual,
title = "Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer",
author = "Yang, Ziqing and
Ma, Wentao and
Cui, Yiming and
Ye, Jiani and
Che, Wanxiang and
Wang, Shijin",
editor = "Fisch, Adam and
Talmor, Alon and
Chen, Danqi and
Choi, Eunsol and
Seo, Minjoon and
Lewis, Patrick and
Jia, Robin and
Min, Sewon",
booktitle = "Proceedings of the 3rd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrqa-1.10",
doi = "10.18653/v1/2021.mrqa-1.10",
pages = "100--105",
abstract = "Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-bilingual">
<titleInfo>
<title>Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziqing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wentao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiani</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijin</namePart>
<namePart type="family">Wang</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>Proceedings of the 3rd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</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 achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.</abstract>
<identifier type="citekey">yang-etal-2021-bilingual</identifier>
<identifier type="doi">10.18653/v1/2021.mrqa-1.10</identifier>
<location>
<url>https://aclanthology.org/2021.mrqa-1.10</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>100</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer
%A Yang, Ziqing
%A Ma, Wentao
%A Cui, Yiming
%A Ye, Jiani
%A Che, Wanxiang
%A Wang, Shijin
%Y Fisch, Adam
%Y Talmor, Alon
%Y Chen, Danqi
%Y Choi, Eunsol
%Y Seo, Minjoon
%Y Lewis, Patrick
%Y Jia, Robin
%Y Min, Sewon
%S Proceedings of the 3rd Workshop on Machine Reading for Question Answering
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F yang-etal-2021-bilingual
%X Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.
%R 10.18653/v1/2021.mrqa-1.10
%U https://aclanthology.org/2021.mrqa-1.10
%U https://doi.org/10.18653/v1/2021.mrqa-1.10
%P 100-105
Markdown (Informal)
[Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer](https://aclanthology.org/2021.mrqa-1.10) (Yang et al., MRQA 2021)
ACL