<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hede-etal-2026-mtg">
    <titleInfo>
        <title>MTG-LIRA: Scaling Neural Machine Translation for Low-Resource Indian Languages through Multilingual Learning and Synthetic Data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vedarth</namePart>
        <namePart type="family">Hede</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Neha</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Harish</namePart>
        <namePart type="family">Bapat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Harsh</namePart>
        <namePart type="family">Ekbote</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>MTG-LIRA’s submission for the WMT 2026 Low-Resource Indic Language Translation Shared Task presents a unified, scalable multilingual Transformer architecture developed using OpenNMT-py to address severe data scarcity across several low-resource Indian languages. The framework partitions languages into family-based groupings—such as Indo-Aryan and Tibeto-Burman—to optimize cross-lingual knowledge sharing and vocabulary overlap using Byte Pair Encoding (BPE). Data preparation integrates official WMT datasets, the BPCC multilingual corpus, and ~5 million synthetic English–Mizo sentence pairs generated via Meta’s NLLB model, all cleaned using a rigorous preprocessing pipeline. Experimental results across task directions demonstrate that combining multilingual base models with targeted, language-specific adaptation strategies yields significant gains: fine-tuning on domain-specific data improved BLEU scores for English→Assamese (12.17 to 14.44) and English→Mizo (16.2 to 22.72); checkpoint averaging of the 5 best models enhanced stability for English\ensuremathłeftrightarrowManipuri (Meitei Mayek); a weighted 3:1 checkpoint averaging strategy improved performance for English→Bodo; and zero-shot style direct transfer proved effective for Assamese→English and English→Manipuri (Bengali script) due to shared script features.</abstract>
    <identifier type="citekey">hede-etal-2026-mtg</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.153/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2146</start>
            <end>2153</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MTG-LIRA: Scaling Neural Machine Translation for Low-Resource Indian Languages through Multilingual Learning and Synthetic Data
%A Hede, Vedarth
%A Gupta, Neha
%A Bapat, Harish
%A Ekbote, Harsh
%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 hede-etal-2026-mtg
%X MTG-LIRA’s submission for the WMT 2026 Low-Resource Indic Language Translation Shared Task presents a unified, scalable multilingual Transformer architecture developed using OpenNMT-py to address severe data scarcity across several low-resource Indian languages. The framework partitions languages into family-based groupings—such as Indo-Aryan and Tibeto-Burman—to optimize cross-lingual knowledge sharing and vocabulary overlap using Byte Pair Encoding (BPE). Data preparation integrates official WMT datasets, the BPCC multilingual corpus, and ~5 million synthetic English–Mizo sentence pairs generated via Meta’s NLLB model, all cleaned using a rigorous preprocessing pipeline. Experimental results across task directions demonstrate that combining multilingual base models with targeted, language-specific adaptation strategies yields significant gains: fine-tuning on domain-specific data improved BLEU scores for English→Assamese (12.17 to 14.44) and English→Mizo (16.2 to 22.72); checkpoint averaging of the 5 best models enhanced stability for English\ensuremathłeftrightarrowManipuri (Meitei Mayek); a weighted 3:1 checkpoint averaging strategy improved performance for English→Bodo; and zero-shot style direct transfer proved effective for Assamese→English and English→Manipuri (Bengali script) due to shared script features.
%U https://aclanthology.org/2026.wmt-main.153/
%P 2146-2153

Markdown (Informal)

[MTG-LIRA: Scaling Neural Machine Translation for Low-Resource Indian Languages through Multilingual Learning and Synthetic Data](https://aclanthology.org/2026.wmt-main.153/) (Hede et al., WMT 2026)

• MTG-LIRA: Scaling Neural Machine Translation for Low-Resource Indian Languages through Multilingual Learning and Synthetic Data (Hede et al., WMT 2026)

ACL

• Vedarth Hede, Neha Gupta, Harish Bapat, and Harsh Ekbote. 2026. MTG-LIRA: Scaling Neural Machine Translation for Low-Resource Indian Languages through Multilingual Learning and Synthetic Data. In Proceedings of the Eleventh Conference on Machine Translation, pages 2146–2153, Budapest, Hungary. Association for Computational Linguistics.