Projects

Developed a solution to improve the accessibility and comprehension of legal documents while accelerating legal research. Utilized DistilBERT, UMAP, and Mini-batch K-Means for legal document clustering, and employed Transformer models from Huggingface for efficient document retrieval based on user queries. Implemented a summarization module using the Pegasus model and created a user-friendly Django website for demonstration. The project was containerized with Docker and deployed on Google Cloud Run for scalability.