@inproceedings{aishwarya-etal-2023-l3cube,
title = "{L}3{C}ube-{I}ndic{N}ews: News-based Short Text and Long Document Classification Datasets in {I}ndic languages",
author = "Mirashi, Aishwarya and
Sonavane, Srushti and
Lingayat, Purva and
Padhiyar, Tejas and
Joshi, Raviraj",
editor = "D. Pawar, Jyoti and
Lalitha Devi, Sobha",
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-1.37",
pages = "442--449",
abstract = "In this work, we introduce L3Cube-IndicNews, a multilingual text classification corpus aimed at curating a high-quality dataset for Indian regional languages, with a specific focus on news headlines and articles. We have centered our work on 10 prominent Indic languages, including Hindi, Bengali, Marathi, Telugu, Tamil, Gujarati, Kannada, Odia, Malayalam, and Punjabi. Each of these news datasets comprises 10 or more classes of news articles. L3CubeIndicNews offers 3 distinct datasets tailored to handle different document lengths that are classified as: Short Headlines Classification (SHC) dataset containing the news headline and news category, Long Document Classification (LDC) dataset containing the whole news article and the news category, and Long Paragraph Classification (LPC) containing sub-articles of the news and the news category. We maintain consistent labeling across all 3 datasets for in-depth length-based analysis. We evaluate each of these Indic language datasets using 4 different models including monolingual BERT, multilingual Indic Sentence BERT (IndicSBERT), and IndicBERT. This research contributes significantly to expanding the pool of available text classification datasets and also makes it possible to develop topic classification models for Indian regional languages. This also serves as an excellent resource for cross-lingual analysis owing to the high overlap of labels among languages. The datasets and models are shared publicly at https://github.com/ l3cube-pune/indic-nlp.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aishwarya-etal-2023-l3cube">
<titleInfo>
<title>L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Mirashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srushti</namePart>
<namePart type="family">Sonavane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Purva</namePart>
<namePart type="family">Lingayat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Padhiyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raviraj</namePart>
<namePart type="family">Joshi</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">Jyoti</namePart>
<namePart type="family">D. Pawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">Lalitha Devi</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>In this work, we introduce L3Cube-IndicNews, a multilingual text classification corpus aimed at curating a high-quality dataset for Indian regional languages, with a specific focus on news headlines and articles. We have centered our work on 10 prominent Indic languages, including Hindi, Bengali, Marathi, Telugu, Tamil, Gujarati, Kannada, Odia, Malayalam, and Punjabi. Each of these news datasets comprises 10 or more classes of news articles. L3CubeIndicNews offers 3 distinct datasets tailored to handle different document lengths that are classified as: Short Headlines Classification (SHC) dataset containing the news headline and news category, Long Document Classification (LDC) dataset containing the whole news article and the news category, and Long Paragraph Classification (LPC) containing sub-articles of the news and the news category. We maintain consistent labeling across all 3 datasets for in-depth length-based analysis. We evaluate each of these Indic language datasets using 4 different models including monolingual BERT, multilingual Indic Sentence BERT (IndicSBERT), and IndicBERT. This research contributes significantly to expanding the pool of available text classification datasets and also makes it possible to develop topic classification models for Indian regional languages. This also serves as an excellent resource for cross-lingual analysis owing to the high overlap of labels among languages. The datasets and models are shared publicly at https://github.com/ l3cube-pune/indic-nlp.</abstract>
<identifier type="citekey">aishwarya-etal-2023-l3cube</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.37</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>442</start>
<end>449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic languages
%A Mirashi, Aishwarya
%A Sonavane, Srushti
%A Lingayat, Purva
%A Padhiyar, Tejas
%A Joshi, Raviraj
%Y D. Pawar, Jyoti
%Y Lalitha Devi, Sobha
%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 aishwarya-etal-2023-l3cube
%X In this work, we introduce L3Cube-IndicNews, a multilingual text classification corpus aimed at curating a high-quality dataset for Indian regional languages, with a specific focus on news headlines and articles. We have centered our work on 10 prominent Indic languages, including Hindi, Bengali, Marathi, Telugu, Tamil, Gujarati, Kannada, Odia, Malayalam, and Punjabi. Each of these news datasets comprises 10 or more classes of news articles. L3CubeIndicNews offers 3 distinct datasets tailored to handle different document lengths that are classified as: Short Headlines Classification (SHC) dataset containing the news headline and news category, Long Document Classification (LDC) dataset containing the whole news article and the news category, and Long Paragraph Classification (LPC) containing sub-articles of the news and the news category. We maintain consistent labeling across all 3 datasets for in-depth length-based analysis. We evaluate each of these Indic language datasets using 4 different models including monolingual BERT, multilingual Indic Sentence BERT (IndicSBERT), and IndicBERT. This research contributes significantly to expanding the pool of available text classification datasets and also makes it possible to develop topic classification models for Indian regional languages. This also serves as an excellent resource for cross-lingual analysis owing to the high overlap of labels among languages. The datasets and models are shared publicly at https://github.com/ l3cube-pune/indic-nlp.
%U https://aclanthology.org/2023.icon-1.37
%P 442-449
Markdown (Informal)
[L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic languages](https://aclanthology.org/2023.icon-1.37) (Mirashi et al., ICON 2023)
ACL