<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="subedi-karki-2026-brs">
    <titleInfo>
        <title>BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bipesh</namePart>
        <namePart type="family">Subedi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nischal</namePart>
        <namePart type="family">Karki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eleventh Conference on Machine Translation</title>
        </titleInfo>
        <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">Philipp</namePart>
            <namePart type="family">Koehn</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">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>This paper describes our submission to the WMT 2026 Low-Resource Indic Language Translation Shared Task for the English-Assamese and English-Bodo pairs in both translation directions. We fine-tune the pretrained NLLB-200 distilled 600M model for primary as well as contrastive tasks. Since Bodo is not supported by NLLB-200, we use the Hindi (hin_Deva) language tag as a proxy for Bodo during fine-tuning and inference, based on an empirical evaluation of Devanagari-script language tags. The constrained systems are trained exclusively on the official task data, while the contrastive systems additionally incorporate publicly available parallel corpora, including AI4Bharat BPCC and Google Smol. A rigorous preprocessing pipeline, combined with the extra parallel data, yields consistent gains across all automatic metrics, with the largest improvements observed for the lower-resource English-Bodo pair.</abstract>
    <identifier type="citekey">subedi-karki-2026-brs</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.164/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2239</start>
            <end>2246</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation
%A Subedi, Bipesh
%A Karki, Nischal
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F subedi-karki-2026-brs
%X This paper describes our submission to the WMT 2026 Low-Resource Indic Language Translation Shared Task for the English-Assamese and English-Bodo pairs in both translation directions. We fine-tune the pretrained NLLB-200 distilled 600M model for primary as well as contrastive tasks. Since Bodo is not supported by NLLB-200, we use the Hindi (hin_Deva) language tag as a proxy for Bodo during fine-tuning and inference, based on an empirical evaluation of Devanagari-script language tags. The constrained systems are trained exclusively on the official task data, while the contrastive systems additionally incorporate publicly available parallel corpora, including AI4Bharat BPCC and Google Smol. A rigorous preprocessing pipeline, combined with the extra parallel data, yields consistent gains across all automatic metrics, with the largest improvements observed for the lower-resource English-Bodo pair.
%U https://aclanthology.org/2026.wmt-main.164/
%P 2239-2246

Markdown (Informal)

[BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation](https://aclanthology.org/2026.wmt-main.164/) (Subedi & Karki, WMT 2026)

• BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation (Subedi & Karki, WMT 2026)

ACL

• Bipesh Subedi and Nischal Karki. 2026. BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 2239–2246, Budapest, Hungary. Association for Computational Linguistics.