Medical Dialogue Virtual Roundtable

Join CMU professors Carolyn Rose, Zachary Chase Lipton and Eric Nyberg, along with government and industry professionals Danica Marinac-Dabic and Sandeep Konam, for a panel discussion covering current research trends in the understanding and analysis of medical conversations. Topics will include extracting information from medical conversations and creating usable summaries of medical provider/patient conversations.

Recent work on dialogue modeling, medical entity extraction, and event and ordering extraction will be discussed, as well as the completion of knowledge graphs. CMU scientists are working with the National Institutes of Health, healthcare companies and large technology providers to better understand key challenges relating to this work. 

February 24, 2021 | 2–4 p.m. ET

RSVPs Closed

A recording of this event can be viewed below


Eric Nyberg Eric Nyberg

Professor, Language Technologies Institute, School of Computer Science

Carnegie Mellon University

Noted for his contributions to the fields of automatic text translation, information retrieval and automatic question answering, Nyberg holds a PhD from Carnegie Mellon University and a B.A. from Boston University. He received the Allen Newell Award for Research Excellence for his contributions to the field of question answering and his work as an original developer on the Watson project. He also earned the Boston University Computer Science Distinguished Alumna/Alumnus Award. Eric directs CMU's Master of Computational Data Science program. He is also co-founder and chief data scientist at Cognistx, and serves on the scientific advisory board for



Carolyn Penstein Rosé

Professor, Language Technologies Institute and Human-Computer Interaction Institute, School of Computer Science

Carnegie Mellon University 

Carolyn Penstein Rosé is a professor in the Language Technologies Institute and Human-Computer Interaction Institute in CMU's School of Computer Science, and a research consultant for the National Institutes of Health in the Epidemiology and Biostatistics division of the Rehabilitation Medicine Department. Her research program focuses on computational modeling of discourse to enable scientific understanding of the social and pragmatic nature of conversational interactions of all forms, as well as clinical information extraction from medical records and social media. 

Her research group’s highly interdisciplinary work, published in over 260 peer-reviewed publications, is represented in the top venues of five fields: language technologies, learning sciences, cognitive science, educational technology and human-computer interaction. Their work has earned awards in three of these fields. She is a past president and inaugural fellow of the International Society of the Learning Sciences, a senior member of IEEE, founding chair of the International Alliance to Advance Learning in the Digital Era, and co-editor-in-chief of the International Journal of Computer-Supported Collaborative Learning. She also serves as a 2020-2021 AAAS fellow under the Leshner Institute for Public Engagement With Science, focusing on public engagement with AI.


Zachary Chase Lipton

Assistant Professor, Operations Research, Tepper School of Business and Machine Learning Department, School of Computer Science

Carnegie Mellon University 

Zachary Chase Lipton is an assistant professor at Carnegie Mellon appointed in both the Machine Learning Department and Tepper School of Business. His research spans core machine learning methods and their social impact, and addresses diverse application areas, including clinical medicine and natural language processing. His current research focuses include robustness under distribution shift, breast cancer screening, the effective and equitable allocation of organs, and the intersection of causal thinking with messy data. He founded the Approximately Correct blog and created Dive Into Deep Learning, an interactive open-source book drafted entirely through Jupyter notebooks. He can be found on Twitter (@zacharylipton) or GitHub (@zackchase).

Sandeep Konamspeaker-placeholder-bio.jpg



Sandeep Konam is the co-founder and CTO of Abridge, which uses machine learning to help people understand and follow through on their doctors' advice. Previously, he built multiple health-tech tools, including a web app to match cancer patients to clinical trials, an augmented reality app to aid low vision patients, and a mobile app to analyze blood-sample images and detect cancer biomarkers. He earned a master's degree in robotics from CMU where he worked on multi-robot coordination, the interpretability of deep learning models, and enhancing UAVs' perception capabilities. Sandeep is also the founder of Hitloop, a human-in-the-loop platform to improve the reliability of machine learning systems, and Konam Foundation, a nonprofit using technology to achieve the Sustainable Development Goals.


Danica Marinac-Dabic danica-marinac-dabic-photo

Associate Director, Office of Clinical Evidence and Analysis Center for Devices and Radiological Health

US Food and Drug Administration (FDA)

Danica Marinac-Dabic, MD, serves as the associate director of the Office of Clinical Evidence and Analysis at the Food and Drug Administration (FDA) Center for Devices and Radiological Health (CDRH). Prior to this position, she was the director of the CDRH Division of Epidemiology. Dr. Marinac-Dabic has over 25 years of experience in obstetrics, gynecology, perinatal epidemiology, and regulatory science and surveillance settings. Under her leadership, in 2010 the FDA launched its Medical Device Epidemiology Network (MDEpiNet) to advance the national/international infrastructure (via public private partnership) and innovative methodological approaches to conducting robust studies and surveillance of medical devices. In 2016, Dr. Marinac-Dabic was inducted as a fellow of the International Society for Pharmacoepidemiology and Therapeutic Risk Management (ISPE). Since 2016, Dr. Marinac-Dabic has spearheaded the interoperable Coordinated Registry Networks (CRNs) via ecosystem partnership in 12 clinical areas by linking the national registries data to claims, EHRs and patient-generated data.