@inproceedings{padakanti-etal-2024-towards,
title = "Towards Enhancing Knowledge Accessibility for Low-Resource {I}ndian Languages: A Template Based Approach",
author = "Padakanti, Srijith and
Aravapalli, Akhilesh and
Chelpuri, Abhijith and
Mamidi, Radhika",
editor = "Lalitha Devi, Sobha and
Arora, Karunesh",
booktitle = "Proceedings of the 21st International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2024",
address = "AU-KBC Research Centre, Chennai, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2024.icon-1.38/",
pages = "332--336",
abstract = "In today`s digital age, access to knowledge and information is crucial for societal growth. Although widespread resources like Wikipedia exist, there is still a linguistic barrier to breakdown for low-resource languages. In India, millions of individuals still lack access to reliable information from Wikipedia because they are only proficient in their regional language. To address this gap, our work focuses on enhancing the content and digital footprint of multiple Indian languages. The primary objective of our work is to improve knowledge accessibility by generating a substantial volume of high-quality Wikipedia articles in Telugu, a widely spoken language in India with around 95.7 million native speakers. Our work aims to create Wikipedia articles and also ensures that each article meets necessary quality standards such as a minimum word count, inclusion of images for reference, and an infobox. Our work also adheres to the five core principles of Wikipedia. We streamline our article generation process, leveraging NLP techniques such as translation, transliteration, and template generation and incorporating human intervention when necessary. Our contribution is a collection of 8,929 articles in the movie domain, now ready to be published on Telugu Wikipedia."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="padakanti-etal-2024-towards">
<titleInfo>
<title>Towards Enhancing Knowledge Accessibility for Low-Resource Indian Languages: A Template Based Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srijith</namePart>
<namePart type="family">Padakanti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhilesh</namePart>
<namePart type="family">Aravapalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhijith</namePart>
<namePart type="family">Chelpuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Mamidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">Lalitha Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karunesh</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">AU-KBC Research Centre, Chennai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In today‘s digital age, access to knowledge and information is crucial for societal growth. Although widespread resources like Wikipedia exist, there is still a linguistic barrier to breakdown for low-resource languages. In India, millions of individuals still lack access to reliable information from Wikipedia because they are only proficient in their regional language. To address this gap, our work focuses on enhancing the content and digital footprint of multiple Indian languages. The primary objective of our work is to improve knowledge accessibility by generating a substantial volume of high-quality Wikipedia articles in Telugu, a widely spoken language in India with around 95.7 million native speakers. Our work aims to create Wikipedia articles and also ensures that each article meets necessary quality standards such as a minimum word count, inclusion of images for reference, and an infobox. Our work also adheres to the five core principles of Wikipedia. We streamline our article generation process, leveraging NLP techniques such as translation, transliteration, and template generation and incorporating human intervention when necessary. Our contribution is a collection of 8,929 articles in the movie domain, now ready to be published on Telugu Wikipedia.</abstract>
<identifier type="citekey">padakanti-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.icon-1.38/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>332</start>
<end>336</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Enhancing Knowledge Accessibility for Low-Resource Indian Languages: A Template Based Approach
%A Padakanti, Srijith
%A Aravapalli, Akhilesh
%A Chelpuri, Abhijith
%A Mamidi, Radhika
%Y Lalitha Devi, Sobha
%Y Arora, Karunesh
%S Proceedings of the 21st International Conference on Natural Language Processing (ICON)
%D 2024
%8 December
%I NLP Association of India (NLPAI)
%C AU-KBC Research Centre, Chennai, India
%F padakanti-etal-2024-towards
%X In today‘s digital age, access to knowledge and information is crucial for societal growth. Although widespread resources like Wikipedia exist, there is still a linguistic barrier to breakdown for low-resource languages. In India, millions of individuals still lack access to reliable information from Wikipedia because they are only proficient in their regional language. To address this gap, our work focuses on enhancing the content and digital footprint of multiple Indian languages. The primary objective of our work is to improve knowledge accessibility by generating a substantial volume of high-quality Wikipedia articles in Telugu, a widely spoken language in India with around 95.7 million native speakers. Our work aims to create Wikipedia articles and also ensures that each article meets necessary quality standards such as a minimum word count, inclusion of images for reference, and an infobox. Our work also adheres to the five core principles of Wikipedia. We streamline our article generation process, leveraging NLP techniques such as translation, transliteration, and template generation and incorporating human intervention when necessary. Our contribution is a collection of 8,929 articles in the movie domain, now ready to be published on Telugu Wikipedia.
%U https://aclanthology.org/2024.icon-1.38/
%P 332-336
Markdown (Informal)
[Towards Enhancing Knowledge Accessibility for Low-Resource Indian Languages: A Template Based Approach](https://aclanthology.org/2024.icon-1.38/) (Padakanti et al., ICON 2024)
ACL