@inproceedings{chinnappa-dhandapani-2021-tamil,
title = "{T}amil Lyrics Corpus: Analysis and Experiments",
author = "Chinnappa, Dhivya and
Dhandapani, Praveenraj",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Kumar M, Anand and
Krishnamurthy, Parameswari and
Sherly, Elizabeth",
booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
month = apr,
year = "2021",
address = "Kyiv",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dravidianlangtech-1.1",
pages = "1--9",
abstract = "In this paper, we present a new Tamil lyrics corpus extracted from Tamil movies captured across a range of 65 years (1954 to 2019). We present a detailed corpus analysis showing the nature of Tamil lyrics with respect to lyricists and the year which it was written. We also present similar- ity score across different lyricists based on their song lyrics. We present experi- mental results based on the SOTA BERT Tamil models to identify the lyricists of a song. Finally, we present future research directions encouraging researchers to pur- sue Tamil NLP research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chinnappa-dhandapani-2021-tamil">
<titleInfo>
<title>Tamil Lyrics Corpus: Analysis and Experiments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Praveenraj</namePart>
<namePart type="family">Dhandapani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="family">Kumar M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a new Tamil lyrics corpus extracted from Tamil movies captured across a range of 65 years (1954 to 2019). We present a detailed corpus analysis showing the nature of Tamil lyrics with respect to lyricists and the year which it was written. We also present similar- ity score across different lyricists based on their song lyrics. We present experi- mental results based on the SOTA BERT Tamil models to identify the lyricists of a song. Finally, we present future research directions encouraging researchers to pur- sue Tamil NLP research.</abstract>
<identifier type="citekey">chinnappa-dhandapani-2021-tamil</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.1</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tamil Lyrics Corpus: Analysis and Experiments
%A Chinnappa, Dhivya
%A Dhandapani, Praveenraj
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Kumar M, Anand
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%S Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv
%F chinnappa-dhandapani-2021-tamil
%X In this paper, we present a new Tamil lyrics corpus extracted from Tamil movies captured across a range of 65 years (1954 to 2019). We present a detailed corpus analysis showing the nature of Tamil lyrics with respect to lyricists and the year which it was written. We also present similar- ity score across different lyricists based on their song lyrics. We present experi- mental results based on the SOTA BERT Tamil models to identify the lyricists of a song. Finally, we present future research directions encouraging researchers to pur- sue Tamil NLP research.
%U https://aclanthology.org/2021.dravidianlangtech-1.1
%P 1-9
Markdown (Informal)
[Tamil Lyrics Corpus: Analysis and Experiments](https://aclanthology.org/2021.dravidianlangtech-1.1) (Chinnappa & Dhandapani, DravidianLangTech 2021)
ACL
- Dhivya Chinnappa and Praveenraj Dhandapani. 2021. Tamil Lyrics Corpus: Analysis and Experiments. In Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages, pages 1–9, Kyiv. Association for Computational Linguistics.