@inproceedings{huang-etal-2023-knowledge,
title = "Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation",
author = "Huang, Kaiyu and
Li, Peng and
Ma, Jin and
Yao, Ting and
Liu, Yang",
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.852",
doi = "10.18653/v1/2023.acl-long.852",
pages = "15286--15304",
abstract = "In the real-world scenario, a longstanding goal of multilingual neural machine translation (MNMT) is that a single model can incrementally adapt to new language pairs without accessing previous training data. In this scenario, previous studies concentrate on overcoming catastrophic forgetting while lacking encouragement to learn new knowledge from incremental language pairs, especially when the incremental language is not related to the set of original languages. To better acquire new knowledge, we propose a knowledge transfer method that can efficiently adapt original MNMT models to diverse incremental language pairs. The method flexibly introduces the knowledge from an external model into original models, which encourages the models to learn new language pairs, completing the procedure of knowledge transfer. Moreover, all original parameters are frozen to ensure that translation qualities on original language pairs are not degraded. Experimental results show that our method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2023-knowledge">
<titleInfo>
<title>Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaiyu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>In the real-world scenario, a longstanding goal of multilingual neural machine translation (MNMT) is that a single model can incrementally adapt to new language pairs without accessing previous training data. In this scenario, previous studies concentrate on overcoming catastrophic forgetting while lacking encouragement to learn new knowledge from incremental language pairs, especially when the incremental language is not related to the set of original languages. To better acquire new knowledge, we propose a knowledge transfer method that can efficiently adapt original MNMT models to diverse incremental language pairs. The method flexibly introduces the knowledge from an external model into original models, which encourages the models to learn new language pairs, completing the procedure of knowledge transfer. Moreover, all original parameters are frozen to ensure that translation qualities on original language pairs are not degraded. Experimental results show that our method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.</abstract>
<identifier type="citekey">huang-etal-2023-knowledge</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.852</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.852</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>15286</start>
<end>15304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation
%A Huang, Kaiyu
%A Li, Peng
%A Ma, Jin
%A Yao, Ting
%A Liu, Yang
%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 huang-etal-2023-knowledge
%X In the real-world scenario, a longstanding goal of multilingual neural machine translation (MNMT) is that a single model can incrementally adapt to new language pairs without accessing previous training data. In this scenario, previous studies concentrate on overcoming catastrophic forgetting while lacking encouragement to learn new knowledge from incremental language pairs, especially when the incremental language is not related to the set of original languages. To better acquire new knowledge, we propose a knowledge transfer method that can efficiently adapt original MNMT models to diverse incremental language pairs. The method flexibly introduces the knowledge from an external model into original models, which encourages the models to learn new language pairs, completing the procedure of knowledge transfer. Moreover, all original parameters are frozen to ensure that translation qualities on original language pairs are not degraded. Experimental results show that our method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.
%R 10.18653/v1/2023.acl-long.852
%U https://aclanthology.org/2023.acl-long.852
%U https://doi.org/10.18653/v1/2023.acl-long.852
%P 15286-15304
Markdown (Informal)
[Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation](https://aclanthology.org/2023.acl-long.852) (Huang et al., ACL 2023)
ACL