@inproceedings{sun-etal-2022-alternative,
title = "Alternative Input Signals Ease Transfer in Multilingual Machine Translation",
author = "Sun, Simeng and
Fan, Angela and
Cross, James and
Chaudhary, Vishrav and
Tran, Chau and
Koehn, Philipp and
Guzm{\'a}n, Francisco",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.363",
doi = "10.18653/v1/2022.acl-long.363",
pages = "5291--5305",
abstract = "Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages, particularly cases where higher-resourced languages can benefit lower-resourced ones. While training an MMT model, the supervision signals learned from one language pair can be transferred to the other via the tokens shared by multiple source languages. However, the transfer is inhibited when the token overlap among source languages is small, which manifests naturally when languages use different writing systems. In this paper, we tackle inhibited transfer by augmenting the training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. We test these signals on Indic and Turkic languages, two language families where the writing systems differ but languages still share common features. Our results indicate that a straightforward multi-source self-ensemble {--} training a model on a mixture of various signals and ensembling the outputs of the same model fed with different signals during inference, outperforms strong ensemble baselines by 1.3 BLEU points on both language families. Further, we find that incorporating alternative inputs via self-ensemble can be particularly effective when training set is small, leading to +5 BLEU when only 5{\%} of the total training data is accessible. Finally, our analysis demonstrates that including alternative signals yields more consistency and translates named entities more accurately, which is crucial for increased factuality of automated systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2022-alternative">
<titleInfo>
<title>Alternative Input Signals Ease Transfer in Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simeng</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Cross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishrav</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chau</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Guzmán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages, particularly cases where higher-resourced languages can benefit lower-resourced ones. While training an MMT model, the supervision signals learned from one language pair can be transferred to the other via the tokens shared by multiple source languages. However, the transfer is inhibited when the token overlap among source languages is small, which manifests naturally when languages use different writing systems. In this paper, we tackle inhibited transfer by augmenting the training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. We test these signals on Indic and Turkic languages, two language families where the writing systems differ but languages still share common features. Our results indicate that a straightforward multi-source self-ensemble – training a model on a mixture of various signals and ensembling the outputs of the same model fed with different signals during inference, outperforms strong ensemble baselines by 1.3 BLEU points on both language families. Further, we find that incorporating alternative inputs via self-ensemble can be particularly effective when training set is small, leading to +5 BLEU when only 5% of the total training data is accessible. Finally, our analysis demonstrates that including alternative signals yields more consistency and translates named entities more accurately, which is crucial for increased factuality of automated systems.</abstract>
<identifier type="citekey">sun-etal-2022-alternative</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.363</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.363</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5291</start>
<end>5305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alternative Input Signals Ease Transfer in Multilingual Machine Translation
%A Sun, Simeng
%A Fan, Angela
%A Cross, James
%A Chaudhary, Vishrav
%A Tran, Chau
%A Koehn, Philipp
%A Guzmán, Francisco
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F sun-etal-2022-alternative
%X Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages, particularly cases where higher-resourced languages can benefit lower-resourced ones. While training an MMT model, the supervision signals learned from one language pair can be transferred to the other via the tokens shared by multiple source languages. However, the transfer is inhibited when the token overlap among source languages is small, which manifests naturally when languages use different writing systems. In this paper, we tackle inhibited transfer by augmenting the training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. We test these signals on Indic and Turkic languages, two language families where the writing systems differ but languages still share common features. Our results indicate that a straightforward multi-source self-ensemble – training a model on a mixture of various signals and ensembling the outputs of the same model fed with different signals during inference, outperforms strong ensemble baselines by 1.3 BLEU points on both language families. Further, we find that incorporating alternative inputs via self-ensemble can be particularly effective when training set is small, leading to +5 BLEU when only 5% of the total training data is accessible. Finally, our analysis demonstrates that including alternative signals yields more consistency and translates named entities more accurately, which is crucial for increased factuality of automated systems.
%R 10.18653/v1/2022.acl-long.363
%U https://aclanthology.org/2022.acl-long.363
%U https://doi.org/10.18653/v1/2022.acl-long.363
%P 5291-5305
Markdown (Informal)
[Alternative Input Signals Ease Transfer in Multilingual Machine Translation](https://aclanthology.org/2022.acl-long.363) (Sun et al., ACL 2022)
ACL
- Simeng Sun, Angela Fan, James Cross, Vishrav Chaudhary, Chau Tran, Philipp Koehn, and Francisco Guzmán. 2022. Alternative Input Signals Ease Transfer in Multilingual Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5291–5305, Dublin, Ireland. Association for Computational Linguistics.