About

I am a San Francisco based Machine Learning Researcher and Engineer, currently working on delivering cyber-risk analytics to the global cyber-insurance market. I work with terabyte-scale data to develop models using Deep Learning and Matrix Factorization techniques.

I particularly enjoy working with language data and models, and I have set up this blog to document personal research projects. If you have any questions or comments about any of my blog posts here or my work in general, please feel free to email me at tn338 [at] cornell [dot] edu. You can also find me on LinkedIn, Twitter or Google Scholar.

Education

I focused on Machine Learning and Natural Language Processing during my graduate studies and research at Cornell University. During this time, I also had the opportunity to learn about product development and work actively with community-based as well as big tech organizations in New York City. My experiences taught me to think deeply about the sustainability of technological solutions and their human and social impact.

I obtained a Bachelor of Engineering degree from BITS Pilani, India. I also spent some time at the Predictive Technology Lab at University of Virginia as a visiting research scholar. I worked on projects designed and developed for research in public health.

News / Highlights

• June 2022: Our paper BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing is live on arXiv.
• June 2022: Our paper Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models is live on arXiv.
• Jan 2022: Our paper Multitask Prompted Training Enables Zero-Shot Task Generalization is accepted at ICLR 2022 as spotlight.
• Sept 2021: Our project demonstrating how Weak Supervision can be used to detect dataset errors and model limitations won the Impact Award at AllenNLP Hacks 2021 – a hackathon organized by Allen Institute of AI. Slides can be made available upon request.
• June 2020: Our paper Longitudinal Analysis of Cyber-Related Articles is accepted at IEEE International Conference on Data Science in Cyberspace 2020.
• May 2018: Graduated from Cornell University. Class of 2018! [Tweet]
• Mar 2018: Moderated a conversation with Eric Schmidt. [Tweet]
• Aug 2017: Represented the student body at Cornell Tech Campus Dedication ceremony. [Video][Press]
• Aug 2017: Published my summer internship work How We Tagged 14,000 BuzzFeed Quizzes Using K-Means Clustering on BuzzFeed Tech Blog.
• Mar 2017: Our paper A Computational Approach to Perceived Trustworthiness of Airbnb Host Profiles is accepted at AAAI Conference on Web and Social Media 2017.
• Dec 2016: Advised by Dr. Mor Naaman, I began research at the intersection of Natural Language Processing, and Investigative Journalism & Online Trust, Fall 2016.
• Mar 2016: Received the Jacobs Technion - Cornell Institute Scholarship to attend graduate school at Cornell University in Fall 2016.