@inproceedings{chinnappa-dhandapani-2021-tamil,
title = "{T}amil Lyrics Corpus: Analysis and Experiments",
author = "Chinnappa, Dhivya and
Dhandapani, Praveenraj",
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.",
}
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.