Dr. Bhagavatula is a Senior Research Scientist at the Allen Institute for AI. His primary research interests are in commonsense reasoning and natural language generation, with broad interests at the intersection of commonsense and vision. He is a co-recipient of the AAAI Outstanding paper award in 2020. He received his Ph.D. in Computer Science from Northwestern University and B.Tech at the National Institute of Technology (Allahabad) in India.
- Commonsense Reasoning
- Natural Language Generation
- Doctor of Philosophy (PhD) in Computer Science, Northwestern University, Evanston, USA
- Bachelors of Technology in Computer Science and Engineering, National Institute of Technology, Allahabad, India
- ME Peters, W Ammar, C Bhagavatula, R Power: (2017) “Semi-supervised sequence tagging with bidirectional language models”, Annual Conference of the Association for Computational Linguistics.
- M Sap, R Le Bras, E Allaway, C Bhagavatula, N Lourie, H Rashkin, et al: (2019) “Atomic: An atlas of machine commonsense for if-then reasoning”, Proceedings of the AAAI Conference on Artificial Intelligence 33, 3027-3035.
- W Ammar, D Groeneveld, C Bhagavatula, I Beltagy, M Crawford, et al: (2018) “Construction of the literature graph in semantic scholar” NAACL HLT (Industry Papers).
- K Sakaguchi, RL Bras, C Bhagavatula, Y Choi: (2020) “WINOGRANDE: An adversarial winograd schema challenge at scale” Proceedings of the AAAI Conference on Artificial Intelligence.
- C Bhagavatula, T Noraset, D Downey: (2015) “TabEL: entity linking in web tables”, International Semantic Web Conference, 425-441.
- Bhagavatula, C, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen-tau Yih, and Yejin Choi. (2020) "Abductive Commonsense Reasoning." In ICLR.
- C Bhagavatula, T Noraset, D Downey: (2013) “Methods for exploring and mining tables on Wikipedia”, Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration.
- C Bhagavatula, S Feldman, R Power, W Ammar: (2018) “Content-based citation recommendation” Proceedings of the 2018 Conference of the North American Chapter