
Rajkumar Pujari
Graduate Student
Graduate Research Assistant
Joined department: Fall 2017
Education
I am a 4th year Ph.D. student working with Prof. Dan Goldwasser. I worked on Machine Comprehension for a while before switching to working on better representations for political events and entities via discourse contextualization. I have been working in the field of Natural Language Processing research for 6+ years now, beginning from my junior year in my undergraduate days. Prior to joining Prof. Goldwasser's lab, I worked as a Research Assistant in Prof. Pushpak Bhattacharyya's CFILT lab at the Indian Institute of Technology, Bombay back in India. I completed my undergraduate degree in Computer Science and Engineering from the Indian Institute of Technology, Kharagpur.
Selected Publications
Rajkumar Pujari, and Dan Goldwasser. "Understanding Politics via Contextualized Discourse Processing." arXiv preprint arXiv:2012.15784 (2020).
Rajkumar Pujari and Dan Goldwasser. "Using Natural Language Relations between Answer Choices for Machine Comprehension." In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4010-4015. 2019.
Deepak Gupta, Rajkumar Pujari, Asif Ekbal, Pushpak Bhattacharyya, Anutosh Maitra, Tom Jain, and Shubhashis Sengupta. "Can taxonomy help? Improving semantic question matching using question taxonomy." In Proceedings of the 27th International Conference on Computational Linguistics, pp. 499-513. 2018.
Rajkumar Pujari, Swara Desai, Niloy Ganguly, and Pawan Goyal. "A novel two-stage framework for extracting opinionated sentences from news articles." In Proceedings of TextGraphs-9: the workshop on Graph-based Methods for Natural Language Processing, pp. 25-33. 2014.
Anutosh Maitra, Shubhashis Sengupta, G. E. O. Tom, Sanjay Podder, Rajkumar Pujari, Deepak Gupta, Asif Ekbal, and Pushpak Bhattacharyya. "Utilizing deep learning with an information retrieval mechanism to provide question answering in restricted domains." U.S. Patent Application 15/988,911, filed November 29, 2018.