Lucy Lu Wang, an Assistant Professor at the University of Washington Information School, will present "Biomedical evidence extraction and synthesis."
Lucy Lu Wang is an Assistant Professor in the University of Washington Information School. She also holds Adjunct appointments in Computer Science & Engineering and Biomedical Informatics & Medical Education, and is a Visiting Research Scientist at the Allen Institute for AI. Her research asks whether AI and natural language processing techniques can make sense of scientific output and help people make better healthcare decisions. Her work on supplement interaction detection, COVID-19 text mining, accessibility in scientific publishing, and gender trends in academic publishing has been featured in publications such as Geekwire, VentureBeat, Boing Boing, Axios, and the New York Times.
Healthcare providers and patients need access to the most up-to-date scientific information to make more evidence-based healthcare decisions. However, the rate at which new information is published is overwhelming, making it difficult to tease out what is relevant and high-quality. Automated approaches leveraging AI and NLP can help maximize access to the content of these documents while reducing burden on users. In this talk, I will discuss NLP systems for extracting and synthesizing evidence contained in scientific articles, and the unique challenges we face when evaluating generated text in this specialized domain. I demonstrate how structured domain knowledge can be used to probe and/or address some of these challenges.
DeYoung, J., Beltagy, I., van Zuylen, M., Kuehl, B., & Wang, L. (2021, November). MSˆ2: Multi-Document Summarization of Medical Studies. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 7494-7513).
Wang, L., Tafjord, O., Cohan, A., Jain, S., Skjonsberg, S., Schoenick, C., ... & Ammar, W. (2020, July). SUPP. AI: finding evidence for supplement-drug interactions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (pp. 362-371).
August, T., Wang, L. L., Bragg, J., Hearst, M. A., Head, A., & Lo, K. (2022). Paper plain: Making medical research papers approachable to healthcare consumers with natural language processing. arXiv preprint arXiv:2203.00130.
We continue the CIRSS speaker series in Spring 2023 with a focus on “Knowledge Graphs and Semantic Computing”. We will meet on Fridays, 9-10am Central Time, on Zoom. To join a session, go to the current week’s session and click the “access” link, which will lead you to a calendar entry. There, click the “PARTICIPATE online” button to join a session. Recordings of past talks can be found next to "access" if available. The event is open to the public, and everyone is welcome to attend! This series is hosted by the Center for Informatics Research in Science and Scholarship (CIRSS). If you have any questions, please contact Jana Diesner and Halil Kilicoglu.
This event is sponsored by Center for Informatics Research in Science and Scholarship