@inproceedings{huang-etal-2023-towards,
title = "Towards Higher {P}areto Frontier in Multilingual Machine Translation",
author = "Huang, Yichong and
Feng, Xiaocheng and
Geng, Xinwei and
Li, Baohang and
Qin, Bing",
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.211",
doi = "10.18653/v1/2023.acl-long.211",
pages = "3802--3818",
abstract = "Multilingual neural machine translation has witnessed remarkable progress in recent years. However, the long-tailed distribution of multilingual corpora poses a challenge of Pareto optimization, i.e., optimizing for some languages may come at the cost of degrading the performance of others. Existing balancing training strategies are equivalent to a series of Pareto optimal solutions, which trade off on a Pareto frontierIn Pareto optimization, Pareto optimal solutions refer to solutions in which none of the objectives can be improved without sacrificing at least one of the other objectives. The set of all Pareto optimal solutions forms a Pareto frontier..In this work, we propose a new training framework, Pareto Mutual Distillation (Pareto-MD), towards pushing the Pareto frontier outwards rather than making trade-offs. Specifically, Pareto-MD collaboratively trains two Pareto optimal solutions that favor different languages and allows them to learn from the strengths of each other via knowledge distillation. Furthermore, we introduce a novel strategy to enable stronger communication between Pareto optimal solutions and broaden the applicability of our approach. Experimental results on the widely-used WMT and TED datasets show that our method significantly pushes the Pareto frontier and outperforms baselines by up to +2.46 BLEUOur code will be released upon acceptance..",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2023-towards">
<titleInfo>
<title>Towards Higher Pareto Frontier in Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaocheng</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinwei</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baohang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</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>Multilingual neural machine translation has witnessed remarkable progress in recent years. However, the long-tailed distribution of multilingual corpora poses a challenge of Pareto optimization, i.e., optimizing for some languages may come at the cost of degrading the performance of others. Existing balancing training strategies are equivalent to a series of Pareto optimal solutions, which trade off on a Pareto frontierIn Pareto optimization, Pareto optimal solutions refer to solutions in which none of the objectives can be improved without sacrificing at least one of the other objectives. The set of all Pareto optimal solutions forms a Pareto frontier..In this work, we propose a new training framework, Pareto Mutual Distillation (Pareto-MD), towards pushing the Pareto frontier outwards rather than making trade-offs. Specifically, Pareto-MD collaboratively trains two Pareto optimal solutions that favor different languages and allows them to learn from the strengths of each other via knowledge distillation. Furthermore, we introduce a novel strategy to enable stronger communication between Pareto optimal solutions and broaden the applicability of our approach. Experimental results on the widely-used WMT and TED datasets show that our method significantly pushes the Pareto frontier and outperforms baselines by up to +2.46 BLEUOur code will be released upon acceptance..</abstract>
<identifier type="citekey">huang-etal-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.211</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.211</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3802</start>
<end>3818</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Higher Pareto Frontier in Multilingual Machine Translation
%A Huang, Yichong
%A Feng, Xiaocheng
%A Geng, Xinwei
%A Li, Baohang
%A Qin, Bing
%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-towards
%X Multilingual neural machine translation has witnessed remarkable progress in recent years. However, the long-tailed distribution of multilingual corpora poses a challenge of Pareto optimization, i.e., optimizing for some languages may come at the cost of degrading the performance of others. Existing balancing training strategies are equivalent to a series of Pareto optimal solutions, which trade off on a Pareto frontierIn Pareto optimization, Pareto optimal solutions refer to solutions in which none of the objectives can be improved without sacrificing at least one of the other objectives. The set of all Pareto optimal solutions forms a Pareto frontier..In this work, we propose a new training framework, Pareto Mutual Distillation (Pareto-MD), towards pushing the Pareto frontier outwards rather than making trade-offs. Specifically, Pareto-MD collaboratively trains two Pareto optimal solutions that favor different languages and allows them to learn from the strengths of each other via knowledge distillation. Furthermore, we introduce a novel strategy to enable stronger communication between Pareto optimal solutions and broaden the applicability of our approach. Experimental results on the widely-used WMT and TED datasets show that our method significantly pushes the Pareto frontier and outperforms baselines by up to +2.46 BLEUOur code will be released upon acceptance..
%R 10.18653/v1/2023.acl-long.211
%U https://aclanthology.org/2023.acl-long.211
%U https://doi.org/10.18653/v1/2023.acl-long.211
%P 3802-3818
Markdown (Informal)
[Towards Higher Pareto Frontier in Multilingual Machine Translation](https://aclanthology.org/2023.acl-long.211) (Huang et al., ACL 2023)
ACL
- Yichong Huang, Xiaocheng Feng, Xinwei Geng, Baohang Li, and Bing Qin. 2023. Towards Higher Pareto Frontier in Multilingual Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3802–3818, Toronto, Canada. Association for Computational Linguistics.