报告题目：Med-reader: A Query-based Multisource AI Learner of Medical Publications

报告时间：2023-07-28   15:00-16:00

报告人：Prof. Wenxuan Zhong ，University of Georgia

报告地点：理学院东北楼三楼会议室(302)

Abstract: As the volume and velocity of medical publications have increased at an unprecedented pace, a computational-based learning system is essential to avoid expensive and time-consuming human annotations which in general hinder the deployment of novel therapeutic methods in clinical practice.

　In this talk, I present Med-Reader, a novel multi-channel learning system that can summarize (topic learning), understand (knowledge-graph constructing) and generalize (hypothesis generating) knowledge simultaneously from query-related publications. As with human learner, Med-Reader can access how faithfully a discovered concept is by using data beyond publications and conducting a novel enrichment analysis.