Swarnadeep Saha


Contact Me
My detailed CV
GitHub Profile
Twitter Profile

I am a first year CS PhD student in the UNC NLP lab at the University of North Carolina at Chapel Hill, advised by Prof. Mohit Bansal. I am generously supported by the institute graduate fellowship and a prestigious Munroe and Rebecca Cobey fellowship. Previously, I spent two wonderful years at IBM Research - India building industry-scale Intelligent Tutoring Systems. Precisely, I developed novel machine learning models for Automatic Short Answer Grading (arXiv 2019, CIKM 2018, AIED 2018), content understanding (IJCAI 2019) and other real-world Natural Language Understanding problems in the Education domain.

Before joining IBM Research, I was an M.Tech. student and a Teaching Assistant in the CS department at IIT, Delhi. I was affiliated with the Data Analytics and Intelligence Research Group and was advised by Prof. Mausam. In my master’s thesis, I developed the widely used Open Information Extraction system (Open IE 5.0) (ACL 2017, COLING 2018).

I completed my B.E. in CS from Jadavpur University, India in 2014 and also spent a year working as a Software Developer in the Acrobat Reader team of Adobe Systems, India. I love language and develop computational models for understanding language, primarily in the areas of Information Extraction, Natural Language Inference and Question Answering. My broad research interests are in Natural Language Processing, Computational Linguistics, Machine Learning and Deep Learning.

Recent News

Publications [Google Scholar] [dblp]

Pre-prints and Workshops

Archival Conference Papers



Professional Service