@inproceedings{ahmadi-etal-2025-literary,
title = "Literary Translations and Synthetic Data for Machine Translation of Low-resourced {M}iddle {E}astern Languages",
author = "Ahmadi, Sina and
Hameed, Razhan and
Sennrich, Rico",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Anastasopoulos, Antonis",
booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.iwslt-1.10/",
doi = "10.18653/v1/2025.iwslt-1.10",
pages = "110--118",
ISBN = "979-8-89176-272-5",
abstract = "Middle Eastern languages represent a linguistically diverse landscape, yet few have received substantial attention in language and speech technology outside those with official status. Machine translation, a cornerstone application in computational linguistics, remains particularly underexplored for these predominantly non-standardized, spoken varieties. This paper proposes data alignment and augmentation techniques that leverage monolingual corpora and large language models to create high-quality parallel corpora for low-resource Middle Eastern languages. Through systematic fine-tuning of a pretrained machine translation model in a multilingual framework, our results demonstrate that corpus quality consistently outperforms quantity as a determinant of translation accuracy. Furthermore, we provide empirical evidence that strategic data selection significantly enhances cross-lingual transfer in multilingual translation systems. These findings offer valuable insights for developing machine translation solutions in linguistically diverse, resource-constrained environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmadi-etal-2025-literary">
<titleInfo>
<title>Literary Translations and Synthetic Data for Machine Translation of Low-resourced Middle Eastern Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Razhan</namePart>
<namePart type="family">Hameed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-272-5</identifier>
</relatedItem>
<abstract>Middle Eastern languages represent a linguistically diverse landscape, yet few have received substantial attention in language and speech technology outside those with official status. Machine translation, a cornerstone application in computational linguistics, remains particularly underexplored for these predominantly non-standardized, spoken varieties. This paper proposes data alignment and augmentation techniques that leverage monolingual corpora and large language models to create high-quality parallel corpora for low-resource Middle Eastern languages. Through systematic fine-tuning of a pretrained machine translation model in a multilingual framework, our results demonstrate that corpus quality consistently outperforms quantity as a determinant of translation accuracy. Furthermore, we provide empirical evidence that strategic data selection significantly enhances cross-lingual transfer in multilingual translation systems. These findings offer valuable insights for developing machine translation solutions in linguistically diverse, resource-constrained environments.</abstract>
<identifier type="citekey">ahmadi-etal-2025-literary</identifier>
<identifier type="doi">10.18653/v1/2025.iwslt-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.iwslt-1.10/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>110</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Literary Translations and Synthetic Data for Machine Translation of Low-resourced Middle Eastern Languages
%A Ahmadi, Sina
%A Hameed, Razhan
%A Sennrich, Rico
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F ahmadi-etal-2025-literary
%X Middle Eastern languages represent a linguistically diverse landscape, yet few have received substantial attention in language and speech technology outside those with official status. Machine translation, a cornerstone application in computational linguistics, remains particularly underexplored for these predominantly non-standardized, spoken varieties. This paper proposes data alignment and augmentation techniques that leverage monolingual corpora and large language models to create high-quality parallel corpora for low-resource Middle Eastern languages. Through systematic fine-tuning of a pretrained machine translation model in a multilingual framework, our results demonstrate that corpus quality consistently outperforms quantity as a determinant of translation accuracy. Furthermore, we provide empirical evidence that strategic data selection significantly enhances cross-lingual transfer in multilingual translation systems. These findings offer valuable insights for developing machine translation solutions in linguistically diverse, resource-constrained environments.
%R 10.18653/v1/2025.iwslt-1.10
%U https://aclanthology.org/2025.iwslt-1.10/
%U https://doi.org/10.18653/v1/2025.iwslt-1.10
%P 110-118
Markdown (Informal)
[Literary Translations and Synthetic Data for Machine Translation of Low-resourced Middle Eastern Languages](https://aclanthology.org/2025.iwslt-1.10/) (Ahmadi et al., IWSLT 2025)
ACL