@inproceedings{basit-etal-2024-challenges,
title = "Challenges in {U}rdu Machine Translation",
author = "Basit, Abdul and
Azeemi, Abdul Hameed and
Raza, Agha Ali",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-1.4/",
doi = "10.18653/v1/2024.loresmt-1.4",
pages = "44--49",
abstract = "Recent advancements in Neural Machine Translation (NMT) systems have significantly improved model performance on various translation benchmarks. However, these systems still face numerous challenges when translating low-resource languages such as Urdu. In this work, we highlight the specific issues faced by machine translation systems when translating Urdu language. We first conduct a comprehensive evaluation of English to Urdu Machine Translation with four diverse models: GPT-3.5 (a large language model), opus-mt-en-ur (a bilingual translation model), NLLB (a model trained for translating 200 languages), and IndicTrans2 (a specialized model for translating low-resource Indic languages). The results demonstrate that IndicTrans2 significantly outperforms other models in Urdu Machine Translation. To understand the differences in the performance of these models, we analyze the Urdu word distribution in different training datasets and compare the training methodologies. Finally, we uncover the specific translation issues and provide suggestions for improvements in Urdu machine translation systems."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basit-etal-2024-challenges">
<titleInfo>
<title>Challenges in Urdu Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Basit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="given">Hameed</namePart>
<namePart type="family">Azeemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agha</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Raza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in Neural Machine Translation (NMT) systems have significantly improved model performance on various translation benchmarks. However, these systems still face numerous challenges when translating low-resource languages such as Urdu. In this work, we highlight the specific issues faced by machine translation systems when translating Urdu language. We first conduct a comprehensive evaluation of English to Urdu Machine Translation with four diverse models: GPT-3.5 (a large language model), opus-mt-en-ur (a bilingual translation model), NLLB (a model trained for translating 200 languages), and IndicTrans2 (a specialized model for translating low-resource Indic languages). The results demonstrate that IndicTrans2 significantly outperforms other models in Urdu Machine Translation. To understand the differences in the performance of these models, we analyze the Urdu word distribution in different training datasets and compare the training methodologies. Finally, we uncover the specific translation issues and provide suggestions for improvements in Urdu machine translation systems.</abstract>
<identifier type="citekey">basit-etal-2024-challenges</identifier>
<identifier type="doi">10.18653/v1/2024.loresmt-1.4</identifier>
<location>
<url>https://aclanthology.org/2024.acl-1.4/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>44</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenges in Urdu Machine Translation
%A Basit, Abdul
%A Azeemi, Abdul Hameed
%A Raza, Agha Ali
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F basit-etal-2024-challenges
%X Recent advancements in Neural Machine Translation (NMT) systems have significantly improved model performance on various translation benchmarks. However, these systems still face numerous challenges when translating low-resource languages such as Urdu. In this work, we highlight the specific issues faced by machine translation systems when translating Urdu language. We first conduct a comprehensive evaluation of English to Urdu Machine Translation with four diverse models: GPT-3.5 (a large language model), opus-mt-en-ur (a bilingual translation model), NLLB (a model trained for translating 200 languages), and IndicTrans2 (a specialized model for translating low-resource Indic languages). The results demonstrate that IndicTrans2 significantly outperforms other models in Urdu Machine Translation. To understand the differences in the performance of these models, we analyze the Urdu word distribution in different training datasets and compare the training methodologies. Finally, we uncover the specific translation issues and provide suggestions for improvements in Urdu machine translation systems.
%R 10.18653/v1/2024.loresmt-1.4
%U https://aclanthology.org/2024.acl-1.4/
%U https://doi.org/10.18653/v1/2024.loresmt-1.4
%P 44-49
Markdown (Informal)
[Challenges in Urdu Machine Translation](https://aclanthology.org/2024.acl-1.4/) (Basit et al., LoResMT 2024)
ACL
- Abdul Basit, Abdul Hameed Azeemi, and Agha Ali Raza. 2024. Challenges in Urdu Machine Translation. In Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024), pages 44–49, Bangkok, Thailand. Association for Computational Linguistics.