KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation

Badal Nyalang; Riya Tekcham; Biman Debbarma

KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation

Badal Nyalang, Riya Tekcham, Biman Debbarma

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

KrenTransV0-1 is MWire Labs’ submission to the WMT 2026 Low-Resource Indic MT Shared Task. We achieve #1 primary rank on both English→Khasi and English→Kokborok. The system covers all 11 Northeast Indian language pairs using a hybrid architecture combining fine-tuned IndicTrans2 for Indic-script languages, NLLB-200 1.3B mono fine-tuned models for Latin-script languages, and M2M-100 418M fine-tuned models for three severely data-starved languages that exhibited complete output collapse under NLLB. All submissions are primary, covering the English-to-target direction only. We additionally report a negative reranking result: neither BharatGen PARAM-1 (2.9B) perplexity reranking nor NE-BERT fluency reranking improved over a beam-search baseline, and all final submissions use the baseline decoding configuration.

Anthology ID:: 2026.wmt-main.158
Volume:: Proceedings of the Eleventh Conference on Machine Translation
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venues:: WMT | WS
SIG:: SIGMT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 2193–2198
Language:
URL:: https://aclanthology.org/2026.wmt-main.158/
DOI:
Bibkey:
Cite (ACL):: Badal Nyalang, Riya Tekcham, and Biman Debbarma. 2026. KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 2193–2198, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation (Nyalang et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.158.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{nyalang-etal-2026-krentransv0,
    title = "{K}ren{T}rans{V}0.1: Multi-Model Routing and Reranking for Low-Resource {N}ortheast {I}ndian Translation",
    author = "Nyalang, Badal  and
      Tekcham, Riya  and
      Debbarma, Biman",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wmt-main.158/",
    pages = "2193--2198",
    ISBN = "979-8-89176-474-3",
    abstract = "KrenTransV0-1 is MWire Labs' submission to the WMT 2026 Low-Resource Indic MT Shared Task. We achieve {\#}1 primary rank on both English{\textrightarrow}Khasi and English{\textrightarrow}Kokborok. The system covers all 11 Northeast Indian language pairs using a hybrid architecture combining fine-tuned IndicTrans2 for Indic-script languages, NLLB-200 1.3B mono fine-tuned models for Latin-script languages, and M2M-100 418M fine-tuned models for three severely data-starved languages that exhibited complete output collapse under NLLB. All submissions are primary, covering the English-to-target direction only. We additionally report a negative reranking result: neither BharatGen PARAM-1 (2.9B) perplexity reranking nor NE-BERT fluency reranking improved over a beam-search baseline, and all final submissions use the baseline decoding configuration."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nyalang-etal-2026-krentransv0">
    <titleInfo>
        <title>KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Badal</namePart>
        <namePart type="family">Nyalang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Riya</namePart>
        <namePart type="family">Tekcham</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Biman</namePart>
        <namePart type="family">Debbarma</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>KrenTransV0-1 is MWire Labs’ submission to the WMT 2026 Low-Resource Indic MT Shared Task. We achieve #1 primary rank on both English→Khasi and English→Kokborok. The system covers all 11 Northeast Indian language pairs using a hybrid architecture combining fine-tuned IndicTrans2 for Indic-script languages, NLLB-200 1.3B mono fine-tuned models for Latin-script languages, and M2M-100 418M fine-tuned models for three severely data-starved languages that exhibited complete output collapse under NLLB. All submissions are primary, covering the English-to-target direction only. We additionally report a negative reranking result: neither BharatGen PARAM-1 (2.9B) perplexity reranking nor NE-BERT fluency reranking improved over a beam-search baseline, and all final submissions use the baseline decoding configuration.</abstract>
    <identifier type="citekey">nyalang-etal-2026-krentransv0</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.158/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2193</start>
            <end>2198</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation
%A Nyalang, Badal
%A Tekcham, Riya
%A Debbarma, Biman
%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 nyalang-etal-2026-krentransv0
%X KrenTransV0-1 is MWire Labs’ submission to the WMT 2026 Low-Resource Indic MT Shared Task. We achieve #1 primary rank on both English→Khasi and English→Kokborok. The system covers all 11 Northeast Indian language pairs using a hybrid architecture combining fine-tuned IndicTrans2 for Indic-script languages, NLLB-200 1.3B mono fine-tuned models for Latin-script languages, and M2M-100 418M fine-tuned models for three severely data-starved languages that exhibited complete output collapse under NLLB. All submissions are primary, covering the English-to-target direction only. We additionally report a negative reranking result: neither BharatGen PARAM-1 (2.9B) perplexity reranking nor NE-BERT fluency reranking improved over a beam-search baseline, and all final submissions use the baseline decoding configuration.
%U https://aclanthology.org/2026.wmt-main.158/
%P 2193-2198

Download as File

Markdown (Informal)

[KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation](https://aclanthology.org/2026.wmt-main.158/) (Nyalang et al., WMT 2026)

KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation (Nyalang et al., WMT 2026)

ACL

Badal Nyalang, Riya Tekcham, and Biman Debbarma. 2026. KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 2193–2198, Budapest, Hungary. Association for Computational Linguistics.