Nikita Mehandru

Nikita Mehandru is a Ph.D. student at UC Berkeley pursuing a designated emphasis in Computational Precision Health, and is interested in applying machine learning and causal inference methods to the healthcare space. She is currently focused on designing and evaluating machine translation systems in high-stakes medical settings, and conducting predictive modeling on clinical notes to improve patient outcomes. She holds a master’s degree from the University of Pennsylvania, and a bachelor’s degree from Claremont McKenna College.

Publications:

Sweta Agrawal, Nikita Mehandru, Niloufar Salehi, Marine Carpuat. 2022. Quality Estimation via Backtranslation at the WMT 2022 Quality Estimation Task. Conference on Machine Translation (WMT). 

Nikita Mehandru, Sweta Agrawal, Marine Carpuat, Niloufar Salehi. 2022. Evaluating the Quality of Machine Translation in Medical Settings. Second Workshop on Bridging Human‑Computer Interaction and Natural Language Processing at NAACL 2022. 

Nikita Mehandru, Samantha Robertson, and Niloufar Salehi. 2022. Reliable and Safe Use of Machine Translation in Medical Settings. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT 2022).

Wesley Hanwen Deng, Nikita Mehandru, Samantha Robertson, and Niloufar Salehi. 2022. Beyond General Purpose Machine Translation: The Need for Context-specific Empirical Research to Design for Appropriate User Trust. Workshop on Trust and Reliance in AI-Human Teams, at CHI 2022.

Steven Weber and Nikita Mehandru. 2022. The 2020s political economy of machine translation. Business and Politics, 24(1), 96–112.