<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hb-etal-2026-tip">
    <titleInfo>
        <title>TIP-RBG-AI: Overcoming Orthographic Discrepancies via Algorithmic Translinear Pipelines and Phylogenetic Script Mapping</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Barathi</namePart>
        <namePart type="given">Ganesh</namePart>
        <namePart type="family">Hb</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michal</namePart>
        <namePart type="family">Ptaszynski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Meenakshi</namePart>
        <namePart type="family">Sharma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jairam</namePart>
        <namePart type="family">R</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 details the submission of team TIP- RBG-AI for the WMT26 Indic-MT shared task. Addressing severe data sparsity, unstandardized orthographies, and script-level discrepancies across ten Indic languages, we introduce a robust, resource-agnostic cross-lingual framework. Rather than relying on standard downstream parameter fine-tuning, our methodology optimizes zero-shot inference topologies across three massively multilingual machine translation architectures: NLLB-200, MADLAD-400, and IndicTrans2. To systematically resolve vocabulary mismatch and tokenizer fragmentation, we implement a three-tiered preprocessing pipeline comprising baseline untuned direct inference for native scripts, translinear normalization via algorithmic back-transliteration for Romanized textual representations, and phylogenetic script mapping for undocumented, scriptless vernaculars. Empirical evaluations demonstrate that structurally aligning orthographic decoding environments and exploiting cross-lingual family networks substantially enriches semantic fidelity. Without executing a single downstream parameter update, our purely zero-shot framework secured multiple podium placements, including second-place finishes in the Bodo and Manipuri (Meitei Mayek) to English tracks, validating the potential of frontend representation alignment for moderate low-resource translation, while also exposing clear limits at the most extreme end of data scarcity. The code used for reproducing the experiments is publicly available at https: //github.com/rbg-research/EMNLP-2026.</abstract>
    <identifier type="citekey">hb-etal-2026-tip</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.152/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2135</start>
            <end>2145</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TIP-RBG-AI: Overcoming Orthographic Discrepancies via Algorithmic Translinear Pipelines and Phylogenetic Script Mapping
%A Hb, Barathi Ganesh
%A Ptaszynski, Michal
%A Sharma, Meenakshi
%A R, Jairam
%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 hb-etal-2026-tip
%X This paper details the submission of team TIP- RBG-AI for the WMT26 Indic-MT shared task. Addressing severe data sparsity, unstandardized orthographies, and script-level discrepancies across ten Indic languages, we introduce a robust, resource-agnostic cross-lingual framework. Rather than relying on standard downstream parameter fine-tuning, our methodology optimizes zero-shot inference topologies across three massively multilingual machine translation architectures: NLLB-200, MADLAD-400, and IndicTrans2. To systematically resolve vocabulary mismatch and tokenizer fragmentation, we implement a three-tiered preprocessing pipeline comprising baseline untuned direct inference for native scripts, translinear normalization via algorithmic back-transliteration for Romanized textual representations, and phylogenetic script mapping for undocumented, scriptless vernaculars. Empirical evaluations demonstrate that structurally aligning orthographic decoding environments and exploiting cross-lingual family networks substantially enriches semantic fidelity. Without executing a single downstream parameter update, our purely zero-shot framework secured multiple podium placements, including second-place finishes in the Bodo and Manipuri (Meitei Mayek) to English tracks, validating the potential of frontend representation alignment for moderate low-resource translation, while also exposing clear limits at the most extreme end of data scarcity. The code used for reproducing the experiments is publicly available at https: //github.com/rbg-research/EMNLP-2026.
%U https://aclanthology.org/2026.wmt-main.152/
%P 2135-2145

Markdown (Informal)

[TIP-RBG-AI: Overcoming Orthographic Discrepancies via Algorithmic Translinear Pipelines and Phylogenetic Script Mapping](https://aclanthology.org/2026.wmt-main.152/) (Hb et al., WMT 2026)

• TIP-RBG-AI: Overcoming Orthographic Discrepancies via Algorithmic Translinear Pipelines and Phylogenetic Script Mapping (Hb et al., WMT 2026)

ACL

• Barathi Ganesh Hb, Michal Ptaszynski, Meenakshi Sharma, and Jairam R. 2026. TIP-RBG-AI: Overcoming Orthographic Discrepancies via Algorithmic Translinear Pipelines and Phylogenetic Script Mapping. In Proceedings of the Eleventh Conference on Machine Translation, pages 2135–2145, Budapest, Hungary. Association for Computational Linguistics.