Author's implementation of the paper https://www.aclweb.org/anthology/2021.dravidianlangtech-1.30/

Author's implementation of the paper https://www.aclweb.org/anthology/2021.ltedi-1.30/

Contextualized Topic Modeling using Zero-Shot Learning on Indic Languages (IndicCTM)

Understanding the sentiment of customers from product reviews using IndicBERT

In order to encourage constructive online debates, content control is crucial on social media sites. In this group project, participants are asked to create systems to handle offensive stretches of code-mixed social media material in Tamil.

A python package to run contextualized topic modeling for Indic Languages. indicCTMs combine contextualized embeddings (e.g., IndicBERT) with topic models to get coherent topics in Hindi, English, and Tamil.

Developed an SRL system using statistical and neural models to label semantic roles in Hindi sentences. Achieved up to 95.34% accuracy using IndicBERT and BiLSTM. Includes datasets, code, and model files.