In my research, I develop Natural Language Processing (NLP) and machine learning methods with applications to clinical and pharmaceutical outcomes and public health. I have focused on three major goals in this domain: (a) identifying signs, symptoms, diseases, disorders, and medications from unstructured electronic health records, (b) detecting signals of neurological disorders affecting children and the elderly, and (c) computational models for identifying social and behavioral determinants of health.At the Johns Hopkins School of Medicine, I co-founded the Center for Clinical NLP and served as the NLP Lead at the Institute for Clinical and Translational Research. I was also affiliated with the Center for Population Health Information Technology, the Center for Language and Speech Processing, and the Precision Medicine Analytics Platform.I was co-leading the enterprise-level clinical NLP research at JHU, including deep neural models for clinical concept linking, normalizing 350m medical notes into HL7 Clinical Document Architecture (CDA), deep information extraction for social and behavioral determinants of health, and predicting risk factors in opioid overdose patients. We also provided various NLP research services to JHU clinical community (ranging from pilot work and seed grants to large and fundamental projects).Prior to joining JHU, I was a postdoc/data scientist at the University of Pennsylvania, affiliated with the World Well-Being Project, and then Penn Institute for Biomedical Informatics. Before that, I was a PhD researcher the Center for Spoken Language Understanding (CSLU) at Oregon Health & Science University (OHSU) - part of what used to be the Oregon Graduate Institute (OGI). I worked on computational analysis of disordered language (autism and Alzheimer's) and ontology development for text-to-scene conversion systems. I also studied formal linguistics and I'm very interested in distributional semantics.