深圳大数据研究院

Shenzhen Research Institute of Big Data

深圳大数据研究院

▶ Topic:eHuatuo: Teaching Computer to Read Medical Records

Time & Date :15:00-16:00, August 10, Friday

Venue:207, Cheng Dao Building

Speaker:Prof. Yan Xu

Language:Chinese

Abstract

讲座摘要

Introduce a series of AI systems about electronic medical records as follows: (1) a system translates narrative text in the medical domain into structured representation is in great demand. The system performs three sub-tasks: concept extraction, assertion classification, and relation identification. (2) a system extracts follow-up information from radiology reports. The method may be used as a component in a system which automatically generates follow-up information in a timely fashion. (3) An integrated coreference resolution system exploits Person attributes, contextual semantic clues, and world knowledge. It includes three subsystems: Person coreference system based on three Person attributes, Problem/Treatment/Test system based on numerous contextual semantic extractors and world knowledge, and Pronoun system based on a multi-class support vector machine classifier. (4) an end-to-end temporal relation system includes three subsystems: an event extraction system (conditional random fields (CRF) name entity extraction and their corresponding attribute classifiers), a temporal extraction system (CRF name entity extraction, their corresponding attribute classifiers, and context-free grammar based normalization system), and a temporal relation system (10 multi-support vector machine (SVM) classifiers and a Markov logic networks inference system) using labeled sequential pattern mining, syntactic structures based on parse trees, and results from a coordination classifier. (5) a sentiment classification system identifies thirteen subjective categories and two objective categories in suicide notes. (6) a smart QA service for productivity in hospital and pharmaceutical factory.

Biography

主讲人简介

She is currently an associate professor of the school of Biological Science and Medical Engineering at BUAA. She was awarded as the "Beijing youth elite" from beijing talent plan, Microsoft Asia Research Institute "Star Star" and "Blue Sky Rookie" from BUAA. She is a researcher in Microsoft Research Asia. Her research areas include artificial intelligence, depth learning, machine learning and medical data, especially good at precision medical research. Professor Xu is at the international forefront level in the research of medical large data, and has studied the parallel computing of large medical data in GB or TB, and proposed a weakly supervised machine learning algorithm with few annotations. At the same time, she focuses on electronic medical records of the structural and information mining research topics and the wearing of large data analysis. Professor Xu is responsible for a number of government and industry-funded projects. Funds include the National Natural Science Foundation, the Beijing Natural Science Foundation, the Shenzhen Natural Science Foundation and the Microsoft Asia Research Foundation. Research results have been applied in a number of top three hospitals and enterprise products.

▶ Topic:Chinese Clinical Natural Language Processing: Research Status and Challenges

Time & Date :16:00-17:00, August 10, Friday

Venue:207, Cheng Dao Building

Speaker:Prof. Buzhou Tang

Abstract

讲座摘要

This talk consists of four parts: 1) a brief introduction to clinical natural language processing (NLP), especially for Chinese clinical NLP, will be given; 2) some studies on Chinese clinical NLP tasks, including clinical entity recognization and normalization, clinical entity attribution extraction, temporal information extraction and indexing, etc., will be presented in detail; 3) challenges in Chinese clinical NLP will be discussed ; 4) status of related communities will be introduced.

Biography

主讲人简介

He is an associate professor of the school of computer science at Harbin Institute of Technology, shenzhen (HITSZ). His interests interests cover machine learning, data mining, natural language processing, signal processing and medical informatics. Professor Tang has been awarded more than 10 research funds and has published more than 80 academic papers. He has ever participated in many international challenges as team leader and won them, such as CoNLL-2010, i2b2-2012, ShARe/CLEF-2013, SemEval-2014 and CCKS-2017.