@inproceedings{azadi-etal-2026-multiway,
title = "Multiway Parallel Corpus in Forced Migration Domain for Multilingual Machine Translation",
author = "Azadi, Fatemeh and
Larkin, Samuel and
Lo, Chi-kiu",
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-1.384/",
doi = "10.63317/3gxsf4vr3pjb",
pages = "4889--4901",
abstract = "High-quality domain-specific parallel corpora play a significant role in improving the performance of machine translation (MT) and multilingual natural language processing (NLP) systems in a target domain. However, most existing multilingual parallel corpora focus on general-purpose data, and a majority of highly specialized domains such as forced migration are suffering from lack of multilingual data. In this work, we present a new high-quality 4-way parallel corpus in the forced migration domain. The corpus consists of human-translated journal articles from Forced Migration Review in English, French, Spanish, and Arabic. Our corpus contains data aligned at both document and sentence level in four languages and provides a clean and reliable 4-way parallel resource for multilingual research in forced migration. Using this dataset, we benchmark several open-weight large language models (LLMs), an open-weight multilingual MT system, online closed MT systems, and a closed LLM across 12 translation directions. We further leverage our corpus to improve the MT quality of a top-performing multilingual foundation model with two common domain adaptation approaches, fine-tuning and few-shot prompting. Our results demonstrate the effectiveness of our corpus in improving the translation performance of current models in the forced migration domain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azadi-etal-2026-multiway">
<titleInfo>
<title>Multiway Parallel Corpus in Forced Migration Domain for Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatemeh</namePart>
<namePart type="family">Azadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Larkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi-kiu</namePart>
<namePart type="family">Lo</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>High-quality domain-specific parallel corpora play a significant role in improving the performance of machine translation (MT) and multilingual natural language processing (NLP) systems in a target domain. However, most existing multilingual parallel corpora focus on general-purpose data, and a majority of highly specialized domains such as forced migration are suffering from lack of multilingual data. In this work, we present a new high-quality 4-way parallel corpus in the forced migration domain. The corpus consists of human-translated journal articles from Forced Migration Review in English, French, Spanish, and Arabic. Our corpus contains data aligned at both document and sentence level in four languages and provides a clean and reliable 4-way parallel resource for multilingual research in forced migration. Using this dataset, we benchmark several open-weight large language models (LLMs), an open-weight multilingual MT system, online closed MT systems, and a closed LLM across 12 translation directions. We further leverage our corpus to improve the MT quality of a top-performing multilingual foundation model with two common domain adaptation approaches, fine-tuning and few-shot prompting. Our results demonstrate the effectiveness of our corpus in improving the translation performance of current models in the forced migration domain.</abstract>
<identifier type="citekey">azadi-etal-2026-multiway</identifier>
<identifier type="doi">10.63317/3gxsf4vr3pjb</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.384/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4889</start>
<end>4901</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multiway Parallel Corpus in Forced Migration Domain for Multilingual Machine Translation
%A Azadi, Fatemeh
%A Larkin, Samuel
%A Lo, Chi-kiu
%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 azadi-etal-2026-multiway
%X High-quality domain-specific parallel corpora play a significant role in improving the performance of machine translation (MT) and multilingual natural language processing (NLP) systems in a target domain. However, most existing multilingual parallel corpora focus on general-purpose data, and a majority of highly specialized domains such as forced migration are suffering from lack of multilingual data. In this work, we present a new high-quality 4-way parallel corpus in the forced migration domain. The corpus consists of human-translated journal articles from Forced Migration Review in English, French, Spanish, and Arabic. Our corpus contains data aligned at both document and sentence level in four languages and provides a clean and reliable 4-way parallel resource for multilingual research in forced migration. Using this dataset, we benchmark several open-weight large language models (LLMs), an open-weight multilingual MT system, online closed MT systems, and a closed LLM across 12 translation directions. We further leverage our corpus to improve the MT quality of a top-performing multilingual foundation model with two common domain adaptation approaches, fine-tuning and few-shot prompting. Our results demonstrate the effectiveness of our corpus in improving the translation performance of current models in the forced migration domain.
%R 10.63317/3gxsf4vr3pjb
%U https://aclanthology.org/2026.lrec-1.384/
%U https://doi.org/10.63317/3gxsf4vr3pjb
%P 4889-4901
Markdown (Informal)
[Multiway Parallel Corpus in Forced Migration Domain for Multilingual Machine Translation](https://aclanthology.org/2026.lrec-1.384/) (Azadi et al., LREC 2026)
ACL