Divyansh Kaushik, PhD Student
https://www.cs.cmu.edu/~dkaushik/
I am a PhD student at the Language Technologies Institute in the School of Computer Science at Carnegie Mellon University. I'm fortunate to be advised by Dr. Eduard Hovy and Dr. Zachary Lipton. My interests lie in robustifying NLP with humans in the loop. I am an Amazon Graduate Research Fellow. In prior years, my work has been supported by Pricewaterhouse Coopers and Facebook AI. When I'm not doing research, I can be found roaming the halls of Capitol Hill advocating for science policy or grabbing a snack from the Dirksen Cafeteria. I often tweet about my research or my takes on policy/my advocacy efforts at @dkaushik96.
Research Interests: Human-in-the-Loop Learning, NLP
Publications
Practical Benefits of Feature Feedback Under Distribution Shift
Anurag Katakkar*, Clay Yoo*, Weiqin Wang*, Zachary Lipton, Divyansh Kaushik
Arxiv Preprint, 2021On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study
Divyansh Kaushik, Douwe Kiela, Zachary Lipton, Wen-tau Yih
Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP), 2021Dynabench: Rethinking Benchmarking in NLP
Douwe Kiela, Max Bartolo, Yixin Nie, Divyansh Kaushik, Atticus Geiger, Zhengxuan Wu, Bertie Vidgen, Grusha Prasad, Amanpreet Singh, Pratik Ringshia, Zhiyi Ma, Tristan Thrush, Sebastian Riedel, Zeerak Waseem, Pontus Stenetorp, Robin Jia, Mohit Bansal, Christopher Potts, Adina Williams
North American Chapter of the Association for Computational Linguistics (NAACL), 2021Explaining The Efficacy of Counterfactually-Augmented Data
Divyansh Kaushik, Zachary Lipton
International Conference on Learning Representations (ICLR), 2021Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
Divyansh Kaushik, Zachary Lipton
International Conference on Learning Representations (ICLR), 2020Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
Yifan Wu, Divyansh Kaushik, Ezra Winston, Zachary Lipton
International Conference on Machine Learning (ICML), 2019How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks
Divyansh Kaushik, Zachary Lipton
Empirical Methods in Natural Language Processing (EMNLP), 2018