NLP

An end-to-end NLP system that classifies product feedback by sentiment and topic, redacts PII before any transformer sees the text, and corrects for sarcasm — a failure mode transformer sentiment models systematically miss. Same InferencePipeline instance powers both the REST API and the UI; no logic forks between surfaces. Architecture flowchart LR T["Raw feedback text"] --> R["Redaction(8 PII categories)"] R --> P["Preprocessing(lowercase, URL/mention strip)"] P --> S["Sentiment(RoBERTa 3-class)"] P --> TC["Topic(keyword classifier)"] S --> SA["Sarcasm Adjustment(regex + heuristics)"] SA --> RES["Structured resultsentiment + topic + confidences+ redaction_summary + latency"] TC --> RES RES --> API["FastAPIPOST /predict"] RES --> UI["Streamlit UI"] Each stage is an independently testable component and can be swapped at runtime via constructor injection. replace_* methods on InferencePipeline allow hot-swapping any stage without rebuilding — useful for A/B comparisons and evaluation harnesses. ...

A graduate research project at UIUC (CS 546, Fall 2024) proposing SHERPA — a semi-structured non-parametric memory framework that integrates a knowledge graph with a hierarchical vector store to improve retrieval-augmented generation. Five-person team; this page covers my two contributions: Query Classification and Entity-Relation Extraction. The interesting story isn’t the destination — it’s the experimental funnel. Both contributions involved walking through multiple wrong-fits before landing on the architecture that shipped. ...

Context For my UIUC research project, I worked on SHERPA, a semi-structured RAG framework designed to improve retrieval and reasoning by combining unstructured biomedical text with structured knowledge graphs. Traditional RAG systems rely heavily on vector search over unstructured documents. Our goal was to explore whether adding structured memory through entity-relation extraction and knowledge graph construction could improve retrieval fidelity, reasoning, and answer quality for biomedical question answering. What I Built My contribution focused on two components: query classification and NER / relation extraction for triplet generation. ...

Context During my undergraduate research at SASTRA University, I worked on computer vision and multimodal AI problems across two research directions: semantic segmentation of aerial imagery and dense video captioning for assistive vision. The common thread across both projects was visual understanding: how can deep learning systems interpret complex visual inputs and convert them into useful structured outputs, whether pixel-level land-cover labels or natural-language descriptions of video content? What I Built For my B.Tech thesis, I worked on semantic segmentation of high-resolution aerial imagery using the ISPRS Vaihingen and Potsdam benchmark datasets. The goal was to classify every pixel in urban aerial images into land-cover categories such as buildings, impervious surfaces, vegetation, trees, cars, and clutter. ...