@inproceedings{shuaibo-etal-2022-supervised,
title = "Supervised Contrastive Learning for Cross-lingual Transfer Learning",
author = "Shuaibo, Wang and
Hui, Di and
Hui, Huang and
Siyu, Lai and
Kazushige, Ouchi and
Yufeng, Chen and
Jinan, Xu",
editor = "Sun, Maosong and
Liu, Yang and
Che, Wanxiang and
Feng, Yang and
Qiu, Xipeng and
Rao, Gaoqi and
Chen, Yubo",
booktitle = "Proceedings of the 21st Chinese National Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Nanchang, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2022.ccl-1.78",
pages = "884--895",
abstract = "{``}Multilingual pre-trained representations are not well-aligned by nature, which harms their performance on cross-lingual tasks. Previous methods propose to post-align the multilingual pretrained representations by multi-view alignment or contrastive learning. However, we argue that both methods are not suitable for the cross-lingual classification objective, and in this paper we propose a simple yet effective method to better align the pre-trained representations. On the basis of cross-lingual data augmentations, we make a minor modification to the canonical contrastive loss, to remove false-negative examples which should not be contrasted. Augmentations with the same class are brought close to the anchor sample, and augmentations with different class are pushed apart. Experiment results on three cross-lingual tasks from XTREME benchmark show our method could improve the transfer performance by a large margin with no additional resource needed. We also provide in-detail analysis and comparison between different post-alignment strategies.{''}",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shuaibo-etal-2022-supervised">
<titleInfo>
<title>Supervised Contrastive Learning for Cross-lingual Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Shuaibo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lai</namePart>
<namePart type="family">Siyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ouchi</namePart>
<namePart type="family">Kazushige</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Yufeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Jinan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Nanchang, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Multilingual pre-trained representations are not well-aligned by nature, which harms their performance on cross-lingual tasks. Previous methods propose to post-align the multilingual pretrained representations by multi-view alignment or contrastive learning. However, we argue that both methods are not suitable for the cross-lingual classification objective, and in this paper we propose a simple yet effective method to better align the pre-trained representations. On the basis of cross-lingual data augmentations, we make a minor modification to the canonical contrastive loss, to remove false-negative examples which should not be contrasted. Augmentations with the same class are brought close to the anchor sample, and augmentations with different class are pushed apart. Experiment results on three cross-lingual tasks from XTREME benchmark show our method could improve the transfer performance by a large margin with no additional resource needed. We also provide in-detail analysis and comparison between different post-alignment strategies.”</abstract>
<identifier type="citekey">shuaibo-etal-2022-supervised</identifier>
<location>
<url>https://aclanthology.org/2022.ccl-1.78</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>884</start>
<end>895</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Supervised Contrastive Learning for Cross-lingual Transfer Learning
%A Shuaibo, Wang
%A Hui, Di
%A Hui, Huang
%A Siyu, Lai
%A Kazushige, Ouchi
%A Yufeng, Chen
%A Jinan, Xu
%Y Sun, Maosong
%Y Liu, Yang
%Y Che, Wanxiang
%Y Feng, Yang
%Y Qiu, Xipeng
%Y Rao, Gaoqi
%Y Chen, Yubo
%S Proceedings of the 21st Chinese National Conference on Computational Linguistics
%D 2022
%8 October
%I Chinese Information Processing Society of China
%C Nanchang, China
%G English
%F shuaibo-etal-2022-supervised
%X “Multilingual pre-trained representations are not well-aligned by nature, which harms their performance on cross-lingual tasks. Previous methods propose to post-align the multilingual pretrained representations by multi-view alignment or contrastive learning. However, we argue that both methods are not suitable for the cross-lingual classification objective, and in this paper we propose a simple yet effective method to better align the pre-trained representations. On the basis of cross-lingual data augmentations, we make a minor modification to the canonical contrastive loss, to remove false-negative examples which should not be contrasted. Augmentations with the same class are brought close to the anchor sample, and augmentations with different class are pushed apart. Experiment results on three cross-lingual tasks from XTREME benchmark show our method could improve the transfer performance by a large margin with no additional resource needed. We also provide in-detail analysis and comparison between different post-alignment strategies.”
%U https://aclanthology.org/2022.ccl-1.78
%P 884-895
Markdown (Informal)
[Supervised Contrastive Learning for Cross-lingual Transfer Learning](https://aclanthology.org/2022.ccl-1.78) (Shuaibo et al., CCL 2022)
ACL