[SMM4H] COVID-19-related Nepali Tweets Classification in a Low Resource Setting

Extractive Nepali Question Answering System | Browser Extension & Web Application

This project explores the application of various Language Learning Models (LLMs) for processing and understanding Sanskrit texts. We evaluate models like MuRIL, BERT, SanBERT, and ByT5 to analyze their efficiency in handling the complexities of Sanskrit through fertility score metrics.

This project focuses on automatically identifying multiple Alankars in Hindi poetry using hyrbid models. It handles the complexity of Multi-Label Classification where a single verse may contain multiple figures of speech. It aims to support literary analysis and low-resource language processing through multilabel classification.

This repository contains Python implementations for processing multilingual text data, focusing on language classification and translation tasks. The project addresses two distinct tasks: language classification and English translation, each involving different complexities in the processing of text data.

FAQ Search Application using multilingual sentence transformer model.

This project detects abusive and non-abusive comments in Malayalm Language using the MuRIL Bert model and compares its performance with TF-IDF + SVM and XGBoost. MuRIL outperforms classical models.

AI-powered multilingual occupational coding system with semantic embeddings, cultural context, and adaptive learning.

Hybrid retrieval and RAG research framework for low-resource Bhojpuri and Indic NLP.

News headline classification in English, Hindi, Gujarati & Marathi using MuRIL, DistilBERT & stacking ensemble. Published at Smart Systems 2026.