@inproceedings{devi-lee-2026-erol,
title = "{EROL}: Transformer-Based Multilingual Translation for {N}ortheastern {I}ndian Language Pairs",
author = "Devi, Laishram Thoibisana and
Lee, Grace",
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.148/",
pages = "2094--2100",
ISBN = "979-8-89176-474-3",
abstract = "We present EROL, a multilingual neural machine translation system for four English{--}Indic language pairs: English{\ensuremath{\leftrightarrow}}Assamese, English{\ensuremath{\leftrightarrow}}Bodo, English{\ensuremath{\leftrightarrow}}Manipuri (Bengali script), and English{\ensuremath{\leftrightarrow}}Manipuri (Meitei Mayek). Our systems are built on the Transformer-Base architecture with 6 encoder and 6 decoder layers, a 512-dimensional model size, 2048-dimensional feed-forward networks, and 8 attention heads. We employ shared source and target embeddings, GELU activation, layer normalization, dropout regularization, and byte-pair encoding (BPE) tokenization. The models are trained using the standard sequence-to-sequence cross-entropy objective, providing a simple yet effective baseline for multilingual translation in low-resource settings. Experimental results demonstrate competitive performance across all translation directions, achieving BLEU scores of 25.10 for Assamese{\textrightarrow}English, 23.50 for Bodo{\textrightarrow}English, 22.47 for Manipuri (Bengali){\textrightarrow}English, 24.71 for Manipuri (Meitei Mayek){\textrightarrow}English, 15.31 for English{\textrightarrow}Assamese, 14.25 for English{\textrightarrow}Bodo, 10.21 for English{\textrightarrow}Manipuri (Bengali), and 3.96 for English{\textrightarrow}Manipuri (Meitei Mayek)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devi-lee-2026-erol">
<titleInfo>
<title>EROL: Transformer-Based Multilingual Translation for Northeastern Indian Language Pairs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laishram</namePart>
<namePart type="given">Thoibisana</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="family">Lee</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>We present EROL, a multilingual neural machine translation system for four English–Indic language pairs: English\ensuremathłeftrightarrowAssamese, English\ensuremathłeftrightarrowBodo, English\ensuremathłeftrightarrowManipuri (Bengali script), and English\ensuremathłeftrightarrowManipuri (Meitei Mayek). Our systems are built on the Transformer-Base architecture with 6 encoder and 6 decoder layers, a 512-dimensional model size, 2048-dimensional feed-forward networks, and 8 attention heads. We employ shared source and target embeddings, GELU activation, layer normalization, dropout regularization, and byte-pair encoding (BPE) tokenization. The models are trained using the standard sequence-to-sequence cross-entropy objective, providing a simple yet effective baseline for multilingual translation in low-resource settings. Experimental results demonstrate competitive performance across all translation directions, achieving BLEU scores of 25.10 for Assamese→English, 23.50 for Bodo→English, 22.47 for Manipuri (Bengali)→English, 24.71 for Manipuri (Meitei Mayek)→English, 15.31 for English→Assamese, 14.25 for English→Bodo, 10.21 for English→Manipuri (Bengali), and 3.96 for English→Manipuri (Meitei Mayek).</abstract>
<identifier type="citekey">devi-lee-2026-erol</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.148/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2094</start>
<end>2100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EROL: Transformer-Based Multilingual Translation for Northeastern Indian Language Pairs
%A Devi, Laishram Thoibisana
%A Lee, Grace
%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 devi-lee-2026-erol
%X We present EROL, a multilingual neural machine translation system for four English–Indic language pairs: English\ensuremathłeftrightarrowAssamese, English\ensuremathłeftrightarrowBodo, English\ensuremathłeftrightarrowManipuri (Bengali script), and English\ensuremathłeftrightarrowManipuri (Meitei Mayek). Our systems are built on the Transformer-Base architecture with 6 encoder and 6 decoder layers, a 512-dimensional model size, 2048-dimensional feed-forward networks, and 8 attention heads. We employ shared source and target embeddings, GELU activation, layer normalization, dropout regularization, and byte-pair encoding (BPE) tokenization. The models are trained using the standard sequence-to-sequence cross-entropy objective, providing a simple yet effective baseline for multilingual translation in low-resource settings. Experimental results demonstrate competitive performance across all translation directions, achieving BLEU scores of 25.10 for Assamese→English, 23.50 for Bodo→English, 22.47 for Manipuri (Bengali)→English, 24.71 for Manipuri (Meitei Mayek)→English, 15.31 for English→Assamese, 14.25 for English→Bodo, 10.21 for English→Manipuri (Bengali), and 3.96 for English→Manipuri (Meitei Mayek).
%U https://aclanthology.org/2026.wmt-main.148/
%P 2094-2100
Markdown (Informal)
[EROL: Transformer-Based Multilingual Translation for Northeastern Indian Language Pairs](https://aclanthology.org/2026.wmt-main.148/) (Devi & Lee, WMT 2026)
ACL