<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-etal-2023-nict">
    <titleInfo>
        <title>NICT-AI4B’s Submission to the Indic MT Shared Task in WMT 2023</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raj</namePart>
        <namePart type="family">Dabre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jay</namePart>
        <namePart type="family">Gala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pranjal</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Chitale</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we (Team NICT-AI4B) describe our MT systems that we submit to the Indic MT task in WMT 2023. Our primary system consists of 3 stages: Joint denoising and MT training using officially approved monolingual and parallel corpora, backtranslation and, MT training on original and backtranslated parallel corpora. We observe that backtranslation leads to substantial improvements in translation quality up to 4 BLEU points. We also develop 2 contrastive systems on unconstrained settings, where the first system involves fine-tuning of IndicTrans2 DA models on official parallel corpora and seed data used in AI4Bharat et al, (2023), and the second system involves a system combination of the primary and the aforementioned system. Overall, we manage to obtain high-quality translation systems for the 4 low-resource North-East Indian languages of focus.</abstract>
    <identifier type="citekey">dabre-etal-2023-nict</identifier>
    <identifier type="doi">10.18653/v1/2023.wmt-1.88</identifier>
    <location>
        <url>https://aclanthology.org/2023.wmt-1.88</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>941</start>
            <end>949</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NICT-AI4B’s Submission to the Indic MT Shared Task in WMT 2023
%A Dabre, Raj
%A Gala, Jay
%A Chitale, Pranjal A.
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F dabre-etal-2023-nict
%X In this paper, we (Team NICT-AI4B) describe our MT systems that we submit to the Indic MT task in WMT 2023. Our primary system consists of 3 stages: Joint denoising and MT training using officially approved monolingual and parallel corpora, backtranslation and, MT training on original and backtranslated parallel corpora. We observe that backtranslation leads to substantial improvements in translation quality up to 4 BLEU points. We also develop 2 contrastive systems on unconstrained settings, where the first system involves fine-tuning of IndicTrans2 DA models on official parallel corpora and seed data used in AI4Bharat et al, (2023), and the second system involves a system combination of the primary and the aforementioned system. Overall, we manage to obtain high-quality translation systems for the 4 low-resource North-East Indian languages of focus.
%R 10.18653/v1/2023.wmt-1.88
%U https://aclanthology.org/2023.wmt-1.88
%U https://doi.org/10.18653/v1/2023.wmt-1.88
%P 941-949

Markdown (Informal)

[NICT-AI4B’s Submission to the Indic MT Shared Task in WMT 2023](https://aclanthology.org/2023.wmt-1.88) (Dabre et al., WMT 2023)

• NICT-AI4B’s Submission to the Indic MT Shared Task in WMT 2023 (Dabre et al., WMT 2023)

ACL

• Raj Dabre, Jay Gala, and Pranjal A. Chitale. 2023. NICT-AI4B’s Submission to the Indic MT Shared Task in WMT 2023. In Proceedings of the Eighth Conference on Machine Translation, pages 941–949, Singapore. Association for Computational Linguistics.