Saritha Madhavan


2022

pdf bib
SSN_MLRG1@DravidianLangTech-ACL2022: Troll Meme Classification in Tamil using Transformer Models
Shruthi Hariprasad | Sarika Esackimuthu | Saritha Madhavan | Rajalakshmi Sivanaiah | Angel S
Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages

The ACL shared task of DravidianLangTech-2022 for Troll Meme classification is a binary classification task that involves identifying Tamil memes as troll or not-troll. Classification of memes is a challenging task since memes express humour and sarcasm in an implicit way. Team SSN_MLRG1 tested and compared results obtained by using three models namely BERT, ALBERT and XLNET. The XLNet model outperformed the other two models in terms of various performance metrics. The proposed XLNet model obtained the 3rd rank in the shared task with a weighted F1-score of 0.558.

pdf bib
SSN_MLRG1@LT-EDI-ACL2022: Multi-Class Classification using BERT models for Detecting Depression Signs from Social Media Text
Karun Anantharaman | Angel S | Rajalakshmi Sivanaiah | Saritha Madhavan | Sakaya Milton Rajendram
Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion

DepSign-LT-EDI@ACL-2022 aims to ascer-tain the signs of depression of a person fromtheir messages and posts on social mediawherein people share their feelings and emo-tions. Given social media postings in English,the system should classify the signs of depres-sion into three labels namely “not depressed”,“moderately depressed”, and “severely de-pressed”. To achieve this objective, we haveadopted a fine-tuned BERT model. This solu-tion from team SSN_MLRG1 achieves 58.5%accuracy on the DepSign-LT-EDI@ACL-2022test set.