@inproceedings{xu-etal-2023-language,
title = "Language-Aware Multilingual Machine Translation with Self-Supervised Learning",
author = "Xu, Haoran and
Maillard, Jean and
Goswami, Vedanuj",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.38",
doi = "10.18653/v1/2023.findings-eacl.38",
pages = "526--539",
abstract = "Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize **intra-distillation** to learn more *language-specific* parameters and then show the importance of these language-specific parameters. Next, we propose a novel but simple SSL task, **concurrent denoising**, that co-trains with the MMT task by concurrently denoising monolingual data on both the encoder and decoder. Finally, we apply **intra-distillation** to this co-training approach. Combining these two approaches significantly improves MMT performance, outperforming three state-of-the-art SSL methods by a large margin, e.g., 11.3{\%} and 3.7{\%} improvement on an 8-language and a 15-language benchmark compared with MASS, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-language">
<titleInfo>
<title>Language-Aware Multilingual Machine Translation with Self-Supervised Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Maillard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vedanuj</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize **intra-distillation** to learn more *language-specific* parameters and then show the importance of these language-specific parameters. Next, we propose a novel but simple SSL task, **concurrent denoising**, that co-trains with the MMT task by concurrently denoising monolingual data on both the encoder and decoder. Finally, we apply **intra-distillation** to this co-training approach. Combining these two approaches significantly improves MMT performance, outperforming three state-of-the-art SSL methods by a large margin, e.g., 11.3% and 3.7% improvement on an 8-language and a 15-language benchmark compared with MASS, respectively.</abstract>
<identifier type="citekey">xu-etal-2023-language</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.38</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.38</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>526</start>
<end>539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language-Aware Multilingual Machine Translation with Self-Supervised Learning
%A Xu, Haoran
%A Maillard, Jean
%A Goswami, Vedanuj
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F xu-etal-2023-language
%X Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize **intra-distillation** to learn more *language-specific* parameters and then show the importance of these language-specific parameters. Next, we propose a novel but simple SSL task, **concurrent denoising**, that co-trains with the MMT task by concurrently denoising monolingual data on both the encoder and decoder. Finally, we apply **intra-distillation** to this co-training approach. Combining these two approaches significantly improves MMT performance, outperforming three state-of-the-art SSL methods by a large margin, e.g., 11.3% and 3.7% improvement on an 8-language and a 15-language benchmark compared with MASS, respectively.
%R 10.18653/v1/2023.findings-eacl.38
%U https://aclanthology.org/2023.findings-eacl.38
%U https://doi.org/10.18653/v1/2023.findings-eacl.38
%P 526-539
Markdown (Informal)
[Language-Aware Multilingual Machine Translation with Self-Supervised Learning](https://aclanthology.org/2023.findings-eacl.38) (Xu et al., Findings 2023)
ACL