Papers by Sangeetha S
Thirumurai: A Large Dataset of Tamil Shaivite Poems and Classification of Tamil Pann (2022.lrec-1)
Copied to clipboard
Shankar Mahadevan, Rahul Ponnusamy, Prasanna Kumar Kumaresan, Prabakaran Chandran, Ruba Priyadharshini, Sangeetha S, Bharathi Raja Chakravarthi
| Challenge: | Thirumurai is a collection of Tamil Shaivite poems dating back to the Hindu revival period . a large dataset containing all the Thirumuru poems is under-resourced . |
| Approach: | They propose to use transformers to classify the Tamil Pann and author of each poem . they propose to train models on petabytes of data, such as the common crawl data . |
| Outcome: | The proposed dataset contains all the Thirumurai poems and classifies the Pann and author of each poem using transformer based architectures. |