学术讲座通知

题目：Crowd-powered NLP and Text Mining

主讲人：Prof. SihongXie

时间：2017年6月7日（周三）下午14:00-16:30

地点：科研楼241会议室

内容摘要：

Natural language processing and text mining are fundamental techniques in modern AI and data management, with applications in business and legal intelligence, bioinformatics, social sensing, among many others. Although much progress has been witnessed in developing novel automatic models to capture the uncertainty and information in text data, researchers and practitioners alike are still hungry for high quality labeled data for model training and evaluation. Due to the nature of the tasks, however, obtaining quality labeled text data is non-trivial and costly. Most recently, crowdsourcing has emerged as an inexpensive way to collect labeled data from a crowd of human workers for various machine learning tasks. In this tutorial, certain fundamental NLP and text mining tasks, such as parsing, tagging, information extraction, and sentiment analysis will be introduced. Along with each task, classic algorithms for crowdsourcing labeled data for the task will be surveyed. Lastly, future research directions at the intersection of NLP, text mining and crowdsourcing will be discussed.

校学术委员会

可信分布式计算与服务教育部重点实验室

2017年6月1日

附主讲人介绍：

SihongXie is an Assitant Professor at the Department of Computer Science and Engineering, Lehigh University, Bethlehem. He received his Ph.D. from the Department of Computer Science at the University of Illinois at Chicago (UIC) under the supervision of Prof. Philip S. Yu. His current research focus on managing text data using crowdsourcing and multiple knowledge source fusion, with applications to online commerce, security and trustworthiness, and human-machine interaction. Dr.Xie has published 40 papers in major data mining conferences, such as KDD, WWW, ICDM, with over 660 citations, according to Google Scholar. He holds M.Eng and BS in software engineering from Sun Yat-Sen University in China.