@inproceedings{pakray-etal-2026-findings,
title = "Findings of {WMT} 2026 shared task on Low-resource {I}ndic Languages Translation",
author = "Pakray, Partha and
Pal, Santanu and
Vetagiri, Advaitha and
Singh, Kshetrimayum Boynao and
Dash, Sandeep and
Maji, Arnab and
Lyngdoh, Saralin and
Laitonjam, Lenin and
Jamatia, Anupam and
Das, Ajit and
Warjri, Sunita and
Sharma, Uzzal and
Sambyo, Koj and
Manna, Riyanka",
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.53/",
pages = "1091--1116",
ISBN = "979-8-89176-474-3",
abstract = "This paper presents the findings of the Lowresource Indic Languages Translation Shared Task organized at the Eleventh Conference on Machine Translation (WMT 2026). We evaluated machine translation systems across ten English{--}Indic language pairs spanning three major language families of Northeast India, grouped into moderately resourced and extremely low-resource categories. Built upon the expanded INDICNE-CORP 2.0 dataset, this edition introduced a rigorous, bidirectional multidomain benchmark covering the Healthcare, Political, Travel, Sports, and Entertainment domains to assess real-world generalizability. The task attracted 24 participating teams who deployed diverse methodologies, including parameter-efficient fine-tuning (PEFT) of multilingual foundations, retrieval-augmented generation (RAG) using frontier large language models (LLMs), and hybrid neuro-symbolic decoding constraints. The systems were evaluated using a comprehensive suite of lexical metrics (BLEU, METEOR, TER, ChrF++) and semantic metrics (BERTScore, COMET). Our analysis reveals a persistent performance cliff under extreme data scarcity and a pronounced directional asymmetry, demonstrating that while current architectures readily decode Indic representations into English, they struggle to generate morphologically complex Indic target text. By publicly releasing these datasets, evaluation protocols, and competitive baselines, this shared task establishes a foundation for advancing research in translation technologies for underrepresented and indigenous languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pakray-etal-2026-findings">
<titleInfo>
<title>Findings of WMT 2026 shared task on Low-resource Indic Languages Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santanu</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Advaitha</namePart>
<namePart type="family">Vetagiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kshetrimayum</namePart>
<namePart type="given">Boynao</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Maji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saralin</namePart>
<namePart type="family">Lyngdoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lenin</namePart>
<namePart type="family">Laitonjam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anupam</namePart>
<namePart type="family">Jamatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajit</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunita</namePart>
<namePart type="family">Warjri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uzzal</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koj</namePart>
<namePart type="family">Sambyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riyanka</namePart>
<namePart type="family">Manna</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 presents the findings of the Lowresource Indic Languages Translation Shared Task organized at the Eleventh Conference on Machine Translation (WMT 2026). We evaluated machine translation systems across ten English–Indic language pairs spanning three major language families of Northeast India, grouped into moderately resourced and extremely low-resource categories. Built upon the expanded INDICNE-CORP 2.0 dataset, this edition introduced a rigorous, bidirectional multidomain benchmark covering the Healthcare, Political, Travel, Sports, and Entertainment domains to assess real-world generalizability. The task attracted 24 participating teams who deployed diverse methodologies, including parameter-efficient fine-tuning (PEFT) of multilingual foundations, retrieval-augmented generation (RAG) using frontier large language models (LLMs), and hybrid neuro-symbolic decoding constraints. The systems were evaluated using a comprehensive suite of lexical metrics (BLEU, METEOR, TER, ChrF++) and semantic metrics (BERTScore, COMET). Our analysis reveals a persistent performance cliff under extreme data scarcity and a pronounced directional asymmetry, demonstrating that while current architectures readily decode Indic representations into English, they struggle to generate morphologically complex Indic target text. By publicly releasing these datasets, evaluation protocols, and competitive baselines, this shared task establishes a foundation for advancing research in translation technologies for underrepresented and indigenous languages.</abstract>
<identifier type="citekey">pakray-etal-2026-findings</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.53/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1091</start>
<end>1116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of WMT 2026 shared task on Low-resource Indic Languages Translation
%A Pakray, Partha
%A Pal, Santanu
%A Vetagiri, Advaitha
%A Singh, Kshetrimayum Boynao
%A Dash, Sandeep
%A Maji, Arnab
%A Lyngdoh, Saralin
%A Laitonjam, Lenin
%A Jamatia, Anupam
%A Das, Ajit
%A Warjri, Sunita
%A Sharma, Uzzal
%A Sambyo, Koj
%A Manna, Riyanka
%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 pakray-etal-2026-findings
%X This paper presents the findings of the Lowresource Indic Languages Translation Shared Task organized at the Eleventh Conference on Machine Translation (WMT 2026). We evaluated machine translation systems across ten English–Indic language pairs spanning three major language families of Northeast India, grouped into moderately resourced and extremely low-resource categories. Built upon the expanded INDICNE-CORP 2.0 dataset, this edition introduced a rigorous, bidirectional multidomain benchmark covering the Healthcare, Political, Travel, Sports, and Entertainment domains to assess real-world generalizability. The task attracted 24 participating teams who deployed diverse methodologies, including parameter-efficient fine-tuning (PEFT) of multilingual foundations, retrieval-augmented generation (RAG) using frontier large language models (LLMs), and hybrid neuro-symbolic decoding constraints. The systems were evaluated using a comprehensive suite of lexical metrics (BLEU, METEOR, TER, ChrF++) and semantic metrics (BERTScore, COMET). Our analysis reveals a persistent performance cliff under extreme data scarcity and a pronounced directional asymmetry, demonstrating that while current architectures readily decode Indic representations into English, they struggle to generate morphologically complex Indic target text. By publicly releasing these datasets, evaluation protocols, and competitive baselines, this shared task establishes a foundation for advancing research in translation technologies for underrepresented and indigenous languages.
%U https://aclanthology.org/2026.wmt-main.53/
%P 1091-1116
Markdown (Informal)
[Findings of WMT 2026 shared task on Low-resource Indic Languages Translation](https://aclanthology.org/2026.wmt-main.53/) (Pakray et al., WMT 2026)
ACL
- Partha Pakray, Santanu Pal, Advaitha Vetagiri, Kshetrimayum Boynao Singh, Sandeep Dash, Arnab Maji, Saralin Lyngdoh, Lenin Laitonjam, Anupam Jamatia, Ajit Das, Sunita Warjri, Uzzal Sharma, Koj Sambyo, and Riyanka Manna. 2026. Findings of WMT 2026 shared task on Low-resource Indic Languages Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 1091–1116, Budapest, Hungary. Association for Computational Linguistics.