@inproceedings{dubey-etal-2026-maith,
title = "{M}ait{H} 1.0: A Parallel Corpus and Baseline for Low-Resource {M}aithili-{H}indi Translation",
author = "Dubey, Kamanksha Prasad and
Maurya, Chandresh and
Padmanabh, Kumar",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.676/",
doi = "10.63317/4otutrpimz7y",
pages = "8567--8576",
abstract = "Maithili is one of the 22 official languages recognized in the Indian Constitution. The literature of Maithili is rich; however, due to current socio-political changes, the language is on the verge of extinction. Therefore, it is crucial to develop a corpus for low-resource Indic languages like Maithili to ensure that the dream of ``No Language Left Behind'' (NLLB) is realized. With this in mind, we contribute a corpus (1,05,600 sentences) containing both manually curated and synthetically generated. Additionally, we propose a strong baseline on the Maithali-Hindi pair using multilingual pretrained models such as IndicTrans2, mBART50, mT5, and NLLB-200 distilled. We evaluate the translation systems using standard performance metrics, including BLEU, CHRF2, TER, COMET, METEOR, and BERTScore. Comparative experiments conducted against the existing NLLB dataset (5,50,300 sentence pairs) demonstrate that our proposed dataset consistently yields superior translation quality. Finally, these results demonstrate that, even with a smaller corpus size, high-quality, task-specific data significantly enhance translation accuracy for low-resource Indian languages, such as Maithili."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dubey-etal-2026-maith">
<titleInfo>
<title>MaitH 1.0: A Parallel Corpus and Baseline for Low-Resource Maithili-Hindi Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamanksha</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Dubey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandresh</namePart>
<namePart type="family">Maurya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kumar</namePart>
<namePart type="family">Padmanabh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Maithili is one of the 22 official languages recognized in the Indian Constitution. The literature of Maithili is rich; however, due to current socio-political changes, the language is on the verge of extinction. Therefore, it is crucial to develop a corpus for low-resource Indic languages like Maithili to ensure that the dream of “No Language Left Behind” (NLLB) is realized. With this in mind, we contribute a corpus (1,05,600 sentences) containing both manually curated and synthetically generated. Additionally, we propose a strong baseline on the Maithali-Hindi pair using multilingual pretrained models such as IndicTrans2, mBART50, mT5, and NLLB-200 distilled. We evaluate the translation systems using standard performance metrics, including BLEU, CHRF2, TER, COMET, METEOR, and BERTScore. Comparative experiments conducted against the existing NLLB dataset (5,50,300 sentence pairs) demonstrate that our proposed dataset consistently yields superior translation quality. Finally, these results demonstrate that, even with a smaller corpus size, high-quality, task-specific data significantly enhance translation accuracy for low-resource Indian languages, such as Maithili.</abstract>
<identifier type="citekey">dubey-etal-2026-maith</identifier>
<identifier type="doi">10.63317/4otutrpimz7y</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.676/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8567</start>
<end>8576</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MaitH 1.0: A Parallel Corpus and Baseline for Low-Resource Maithili-Hindi Translation
%A Dubey, Kamanksha Prasad
%A Maurya, Chandresh
%A Padmanabh, Kumar
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F dubey-etal-2026-maith
%X Maithili is one of the 22 official languages recognized in the Indian Constitution. The literature of Maithili is rich; however, due to current socio-political changes, the language is on the verge of extinction. Therefore, it is crucial to develop a corpus for low-resource Indic languages like Maithili to ensure that the dream of “No Language Left Behind” (NLLB) is realized. With this in mind, we contribute a corpus (1,05,600 sentences) containing both manually curated and synthetically generated. Additionally, we propose a strong baseline on the Maithali-Hindi pair using multilingual pretrained models such as IndicTrans2, mBART50, mT5, and NLLB-200 distilled. We evaluate the translation systems using standard performance metrics, including BLEU, CHRF2, TER, COMET, METEOR, and BERTScore. Comparative experiments conducted against the existing NLLB dataset (5,50,300 sentence pairs) demonstrate that our proposed dataset consistently yields superior translation quality. Finally, these results demonstrate that, even with a smaller corpus size, high-quality, task-specific data significantly enhance translation accuracy for low-resource Indian languages, such as Maithili.
%R 10.63317/4otutrpimz7y
%U https://aclanthology.org/2026.lrec-1.676/
%U https://doi.org/10.63317/4otutrpimz7y
%P 8567-8576
Markdown (Informal)
[MaitH 1.0: A Parallel Corpus and Baseline for Low-Resource Maithili-Hindi Translation](https://aclanthology.org/2026.lrec-1.676/) (Dubey et al., LREC 2026)
ACL