I use Machine Learning to model real-world problems in the domain of natural language understanding and information extraction .
More recently, I have been focusing on improving the safety and reliability of Machine Learning models for safety critical applications.
My work uses methods from Probabilistic Graphical Models, Reinforcement Learning, Neural Networks, Convex Optimization etc.
Before starting at UMass, I worked at Samsung in Embedded Software Division. Before that, I was doing my undergrad from Dept of Electrical Engineering, Indian Institute of Technology, Roorkee.
- Jagannatha A., Yu H. Calibrating Structured Output Predictors for Natural Language Processing. ACL 2020
- Jagannatha A., Liu F., Liu W., Yu H. Overview of the first natural language processing challenge for extracting medication, indication, and adverse drug events from electronic health record notes (MADE 1.0). Drug Safety , 2019
- Jagannatha A. N., Thomas P., Yu H.Towards High Confidence Off-Policy Reinforcement Learning for Clinical Applications. ICML 2018 CausalML Workshop
- Jagannatha A., Yu H. Structured Prediction Models for RNN based Sequence Labeling in Clinical Text. EMNLP 2016.
- Jagannatha A., Yu H. Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records. NAACL-HLT 2016 .
Following is a subset of my publications. They broadly cover my main research areas. For a complete list of my papers, please refer to Google Scholar.