#nlp-machine-learning

Explainable, retrieval-based medical question answering chatbot built on NIH-sourced data

End-to-end NLP pipeline for automated contract analysis and risk assessment using CUAD and fine-tuned RoBERTa-Legal. Integrates spaCy NER, rule-based heuristics, and Pinecone for semantic search, with REST API deployment, containerization, and full test coverage for legal/compliance research.

A retrieval-based medical Q&A system that gives accurate answers to diabetes-related questions by searching a curated medical knowledge base instead of generating text from scratch. Built with a hybrid FAISS + BM25 retrieval pipeline, cross-encoder reranking, and multi-layer safety gating and served through a Streamlit web app.