I am a Data Enthusiast with expertise in Machine Learning, Time Series Forecasting, Natural Language Processing and Supply Chain Management. I am passionate about solving real-world problems by making data interpretable to machine learning models and identifying patterns for predicting results. As an avid reader of research papers and technical articles I keep myself up-to-date with the latest advances in the field of data science. My experience in the technology consulting industry involving interaction with stakeholders from multiple industrial sectors makes me a skilled communicator with ability to explain complex technical concepts to non-technical audiences. I am currently working as Data Scientist at Prairie Research Institute within the Watershed Science Research Team. I have built multi-objective optimization frameworks, trained deep learning models for accurate forecasting, and created visualizations. I am also a team player and enjoy working collaboratively with others to achieve common goals. I am always looking for new challenges and opportunities to learn and grow.
I have experience in working on Large Language Model (LLM) applications using RAG (Retrieval-Augmented Generation) and Prompt Engineering using tools like LangChain, Pytorch, and Hugging Face. As a student with a strong academic background in Natural Language Processing (NLP), I am particularly fascinated by the potential of these technologies to revolutionize the way we interact with and understand language. I have gained a comprehensive understanding of NLP fundamentals, including language modeling, machine translation, and question answering. My research focus lies in studying different stages of the NLP pipeline. I have conducted 2 extensive literature reviews involving the study of evolution of models pertaining to Biomedical Named Entity Recognition and Neural Machine Translation. I have been working on multiple academic projects using python libraries such as NLTK, spaCy, genism and Beautiful Soup, TensorFlow and PyTorch. I am currently co-authoring a research paper for reviewing architectures of dialogue systems developed within the NLP community. I have recently implemented a Chatbot using advance RAG techniques working as a virtual assistant to solve dental problems. I am have contanstantly updating it with SOTA techniques for response generation based on the latest updates from the LLM world. My academic experience and passion for NLP and GenAI have equipped me with the necessary skills and knowledge to contribute meaningfully to LLM development projects.
You can find more about my work from my GitHub repositories, Kaggle profile and Linkedin Profile.
Assessment of NER Tools for detecting Funding Organizations (Information Quality Lab, UIUC) Named Entity Recognition (NER) is a key element within the Natural Language Processing (NLP) pipeline of information extraction. NER helps discover valuable insights from textual documents by detecting entities mentioned in unstructured text and categorizing them into predefined categories such as person, organization, location, date, etc. In the past few years, the developers within the NLP community have developed some NER tools for detecting entities such as the organization names. The role of research funders in science is important. In order to better understand NER tools’ accuracy in identifying sponsors in the research funding domain, further research is needed to analyze research funding acknowledgement statements. My Research explores how well existing NER tools recognize funding organizations. Specifically, the most common existing NER tools have been evaluated for their performance to identify scenarios that need improvement, which will enable new research pertaining to Named Entity Recogniton in the research funding field. You can find detials about my work on my github repository- NER-tool-assement-for-funding-organization-extraction
Review of Knowledge Powered Dialog Systems (NCSA, UIUC) I am co-authoring a research paper for conducting review of existing Knowledge-powered Q&A and Dialogue Systems. I have analysed 80 crowd-sourced datasets pertaining to dialogue systems and drafted a comparison of models trained on these datasets. I have also designed a generic architecture of language models responsible for knowledge selection in knowledge grounded dialogue systems.
Dental AI Assistant: A Medical Chatbot built using Retrieval QA chain and Prompt Tuning (NLP)
Neural-Machine-Translation-of-sentences-from-English-to-French