@inproceedings{lin-etal-2021-learning,
title = "Learning Language Specific Sub-network for Multilingual Machine Translation",
author = "Lin, Zehui and
Wu, Liwei and
Wang, Mingxuan and
Li, Lei",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.25",
doi = "10.18653/v1/2021.acl-long.25",
pages = "293--305",
abstract = "Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy adaptation to new language pairs and zero-shot translation. LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at \url{https://github.com/NLP-Playground/LaSS}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2021-learning">
<titleInfo>
<title>Learning Language Specific Sub-network for Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zehui</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liwei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy adaptation to new language pairs and zero-shot translation. LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at https://github.com/NLP-Playground/LaSS.</abstract>
<identifier type="citekey">lin-etal-2021-learning</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.25</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.25</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>293</start>
<end>305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Language Specific Sub-network for Multilingual Machine Translation
%A Lin, Zehui
%A Wu, Liwei
%A Wang, Mingxuan
%A Li, Lei
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F lin-etal-2021-learning
%X Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy adaptation to new language pairs and zero-shot translation. LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at https://github.com/NLP-Playground/LaSS.
%R 10.18653/v1/2021.acl-long.25
%U https://aclanthology.org/2021.acl-long.25
%U https://doi.org/10.18653/v1/2021.acl-long.25
%P 293-305
Markdown (Informal)
[Learning Language Specific Sub-network for Multilingual Machine Translation](https://aclanthology.org/2021.acl-long.25) (Lin et al., ACL-IJCNLP 2021)
ACL
- Zehui Lin, Liwei Wu, Mingxuan Wang, and Lei Li. 2021. Learning Language Specific Sub-network for Multilingual Machine Translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 293–305, Online. Association for Computational Linguistics.