@inproceedings{abdul-rauf-hira-2023-development,
title = "Development of {U}rdu-{E}nglish Religious Domain Parallel Corpus",
author = "Abdul Rauf, Sadaf and
Hira, Noor e",
booktitle = "Proceedings of the Second Workshop on Corpus Generation and Corpus Augmentation for Machine Translation",
month = sep,
year = "2023",
address = "Macau SAR, China",
publisher = "Asia-Pacific Association for Machine Translation",
url = "https://aclanthology.org/2023.mtsummit-coco4mt.2",
pages = "14--21",
abstract = "Despite the abundance of monolingual corpora accessible online, there remains a scarcity of domain specific parallel corpora. This scarcity poses a challenge in the development of robust translation systems tailored for such specialized domains. Addressing this gap, we have developed a parallel religious domain corpus for Urdu-English. This corpus consists of 18,426 parallel sentences from Sunan Daud, carefully curated to capture the unique linguistic and contextual aspects of religious texts. The developed corpus is then used to train Urdu-English religious domain Neural Machine Translation (NMT) systems, the best system scored 27.9 BLEU points",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdul-rauf-hira-2023-development">
<titleInfo>
<title>Development of Urdu-English Religious Domain Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sadaf</namePart>
<namePart type="family">Abdul Rauf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noor</namePart>
<namePart type="given">e</namePart>
<namePart type="family">Hira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Corpus Generation and Corpus Augmentation for Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Asia-Pacific Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Macau SAR, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the abundance of monolingual corpora accessible online, there remains a scarcity of domain specific parallel corpora. This scarcity poses a challenge in the development of robust translation systems tailored for such specialized domains. Addressing this gap, we have developed a parallel religious domain corpus for Urdu-English. This corpus consists of 18,426 parallel sentences from Sunan Daud, carefully curated to capture the unique linguistic and contextual aspects of religious texts. The developed corpus is then used to train Urdu-English religious domain Neural Machine Translation (NMT) systems, the best system scored 27.9 BLEU points</abstract>
<identifier type="citekey">abdul-rauf-hira-2023-development</identifier>
<location>
<url>https://aclanthology.org/2023.mtsummit-coco4mt.2</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>14</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of Urdu-English Religious Domain Parallel Corpus
%A Abdul Rauf, Sadaf
%A Hira, Noor e.
%S Proceedings of the Second Workshop on Corpus Generation and Corpus Augmentation for Machine Translation
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F abdul-rauf-hira-2023-development
%X Despite the abundance of monolingual corpora accessible online, there remains a scarcity of domain specific parallel corpora. This scarcity poses a challenge in the development of robust translation systems tailored for such specialized domains. Addressing this gap, we have developed a parallel religious domain corpus for Urdu-English. This corpus consists of 18,426 parallel sentences from Sunan Daud, carefully curated to capture the unique linguistic and contextual aspects of religious texts. The developed corpus is then used to train Urdu-English religious domain Neural Machine Translation (NMT) systems, the best system scored 27.9 BLEU points
%U https://aclanthology.org/2023.mtsummit-coco4mt.2
%P 14-21
Markdown (Informal)
[Development of Urdu-English Religious Domain Parallel Corpus](https://aclanthology.org/2023.mtsummit-coco4mt.2) (Abdul Rauf & Hira, MTSummit 2023)
ACL