@inproceedings{chindukuri-sangeetha-2023-t20ngd,
title = "{T}20{NGD}: Annotated corpus for news headlines classification in low resource language,{T}elugu.",
author = "Chindukuri, Mallikarjuna and
Sangeetha, Sivanesan",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.35",
pages = "423--432",
abstract = "News classification allows analysts and researchers to study trends over time. Based on classification, news platforms can provide readers with related articles. Many digital news platforms and apps use classification to offer personalized content for their users. While there are numerous resources accessible for news classification in various Indian languages, there is still a lack of extensive benchmark dataset specifically for the Telugu language. Our paper presents and describes the Telugu20news group dataset, where news has been collected from various online Telugu news channels. We describe in detail the accumulation and annotation of the proposed news headlines dataset. In addition, we conducted extensive experiments on our proposed news headlines dataset in order to deliver solid baselines for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chindukuri-sangeetha-2023-t20ngd">
<titleInfo>
<title>T20NGD: Annotated corpus for news headlines classification in low resource language,Telugu.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mallikarjuna</namePart>
<namePart type="family">Chindukuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivanesan</namePart>
<namePart type="family">Sangeetha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>News classification allows analysts and researchers to study trends over time. Based on classification, news platforms can provide readers with related articles. Many digital news platforms and apps use classification to offer personalized content for their users. While there are numerous resources accessible for news classification in various Indian languages, there is still a lack of extensive benchmark dataset specifically for the Telugu language. Our paper presents and describes the Telugu20news group dataset, where news has been collected from various online Telugu news channels. We describe in detail the accumulation and annotation of the proposed news headlines dataset. In addition, we conducted extensive experiments on our proposed news headlines dataset in order to deliver solid baselines for future work.</abstract>
<identifier type="citekey">chindukuri-sangeetha-2023-t20ngd</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.35</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>423</start>
<end>432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T T20NGD: Annotated corpus for news headlines classification in low resource language,Telugu.
%A Chindukuri, Mallikarjuna
%A Sangeetha, Sivanesan
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F chindukuri-sangeetha-2023-t20ngd
%X News classification allows analysts and researchers to study trends over time. Based on classification, news platforms can provide readers with related articles. Many digital news platforms and apps use classification to offer personalized content for their users. While there are numerous resources accessible for news classification in various Indian languages, there is still a lack of extensive benchmark dataset specifically for the Telugu language. Our paper presents and describes the Telugu20news group dataset, where news has been collected from various online Telugu news channels. We describe in detail the accumulation and annotation of the proposed news headlines dataset. In addition, we conducted extensive experiments on our proposed news headlines dataset in order to deliver solid baselines for future work.
%U https://aclanthology.org/2023.icon-1.35
%P 423-432
Markdown (Informal)
[T20NGD: Annotated corpus for news headlines classification in low resource language,Telugu.](https://aclanthology.org/2023.icon-1.35) (Chindukuri & Sangeetha, ICON 2023)
ACL