@inproceedings{oinam-saharia-2025-delab,
title = "{DELAB}-{IIITM} {WMT}25: Enhancing Low-Resource Machine Translation for {M}anipuri and {A}ssamese",
author = "Oinam, Dingku and
Saharia, Navanath",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Tenth Conference on Machine Translation",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wmt-1.98/",
pages = "1222--1226",
ISBN = "979-8-89176-341-8",
abstract = "This paper describe DELAB-IIITM{'}s submission system for the WMT25 machine translation shared task. We participated in two sub-task of the Indic Translation Task, en{\ensuremath{\leftrightarrow}}as and en{\ensuremath{\leftrightarrow}}mn i.e. Assamese (Indo Aryan language) and Manipuri (Tibeto Burman language) with a total of six translation directions, including mn{\textrightarrow}en, mn{\textleftarrow}en, en{\textrightarrow}as, en{\textleftarrow}as, mn{\textrightarrow}as, mn{\textleftarrow}as. Our fine tuning process aims to leverages the pretrained multilingual NLLB-200 model, a machine translation model developed by Meta AI as part of the No Language Left Behind (NLLB) project, through two main development, Synthetic parallel corpus creation and Strategic Fine-tuning. The Fine-tuning process involves strict data cleaning protocols, Adafactor optimizer with low learning rate(2e-5), 2 training epochs, train-test data splits to prevent overfitting, and Seq2SeqTrainer framework. The official test data was used to generate the target language with our fine-tuned model. Experimental results show that our method improves the BLEU scores for translation of these two language pairs. These findings confirm that back-translation remains challenging, largely due to morphological complexity and limited data availability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oinam-saharia-2025-delab">
<titleInfo>
<title>DELAB-IIITM WMT25: Enhancing Low-Resource Machine Translation for Manipuri and Assamese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dingku</namePart>
<namePart type="family">Oinam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navanath</namePart>
<namePart type="family">Saharia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-341-8</identifier>
</relatedItem>
<abstract>This paper describe DELAB-IIITM’s submission system for the WMT25 machine translation shared task. We participated in two sub-task of the Indic Translation Task, en\ensuremathłeftrightarrowas and en\ensuremathłeftrightarrowmn i.e. Assamese (Indo Aryan language) and Manipuri (Tibeto Burman language) with a total of six translation directions, including mn→en, mn←en, en→as, en←as, mn→as, mn←as. Our fine tuning process aims to leverages the pretrained multilingual NLLB-200 model, a machine translation model developed by Meta AI as part of the No Language Left Behind (NLLB) project, through two main development, Synthetic parallel corpus creation and Strategic Fine-tuning. The Fine-tuning process involves strict data cleaning protocols, Adafactor optimizer with low learning rate(2e-5), 2 training epochs, train-test data splits to prevent overfitting, and Seq2SeqTrainer framework. The official test data was used to generate the target language with our fine-tuned model. Experimental results show that our method improves the BLEU scores for translation of these two language pairs. These findings confirm that back-translation remains challenging, largely due to morphological complexity and limited data availability.</abstract>
<identifier type="citekey">oinam-saharia-2025-delab</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.98/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1222</start>
<end>1226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DELAB-IIITM WMT25: Enhancing Low-Resource Machine Translation for Manipuri and Assamese
%A Oinam, Dingku
%A Saharia, Navanath
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F oinam-saharia-2025-delab
%X This paper describe DELAB-IIITM’s submission system for the WMT25 machine translation shared task. We participated in two sub-task of the Indic Translation Task, en\ensuremathłeftrightarrowas and en\ensuremathłeftrightarrowmn i.e. Assamese (Indo Aryan language) and Manipuri (Tibeto Burman language) with a total of six translation directions, including mn→en, mn←en, en→as, en←as, mn→as, mn←as. Our fine tuning process aims to leverages the pretrained multilingual NLLB-200 model, a machine translation model developed by Meta AI as part of the No Language Left Behind (NLLB) project, through two main development, Synthetic parallel corpus creation and Strategic Fine-tuning. The Fine-tuning process involves strict data cleaning protocols, Adafactor optimizer with low learning rate(2e-5), 2 training epochs, train-test data splits to prevent overfitting, and Seq2SeqTrainer framework. The official test data was used to generate the target language with our fine-tuned model. Experimental results show that our method improves the BLEU scores for translation of these two language pairs. These findings confirm that back-translation remains challenging, largely due to morphological complexity and limited data availability.
%U https://aclanthology.org/2025.wmt-1.98/
%P 1222-1226
Markdown (Informal)
[DELAB-IIITM WMT25: Enhancing Low-Resource Machine Translation for Manipuri and Assamese](https://aclanthology.org/2025.wmt-1.98/) (Oinam & Saharia, WMT 2025)
ACL