Lecturer: Dr. Zaiqing Nie (Lead Researcher)
Lecture Time: 2010-5-11 6：00pm~7：30pm
Lecture Place:
Dr. Zaiqing Nie (Lead Researcher)
Zaiqing Nie is a Lead Researcher in the Web Search & Mining Group at Microsoft Research Asia. He graduated in May 2004 with a Ph.D. in Computer Science from Arizona State University. He received both his Master and Bachelor of Engineering degree in Computer Science from Tsinghua University. His research interests include data mining, machine learning, Web information integration and retrieval. Nie has many publications in high quality conferences and journals including SIGKDD, WWW, ICML, CIDR, ICDE, JMLR, and TKDE. His recent academic activities include vice PC chair of ICDM 2010, senior PC of AAAI 2010 (AI and Web track) and PC member of WWW 2010, KDD 2010, ACL 2010, WSDM 2010 etc. Some technologies he developed have been transferred to Microsoft products/services including Bing, Microsoft Academic Search, Renlifang and EntityCube.
Abstract：
Current Web search engine can be considered a page-level general search engine whose main functionality is to rank web pages according to their relevance to a given query. However, there are various kinds of entities (i.e. objects) embedded in static Web pages or Web databases. Typical entities are people, products, papers, organizations, etc. We can imagine that if these entities can be extracted and integrated from the Web, powerful entity search engines can be built to meet users' information needs more precisely. In this talk, I will discuss this new trend on building what we call “object-level search engines”. The research problems that we need to address include large scale Web classification, Web entity extraction and disambiguation, entity relationship mining, and entity ranking. I introduce the overview and core technologies of object-level search engines that have been implemented in three working systems: Microsoft Academic Search (http://academic.research.microsoft.com), Renlifang Guanxi Search (http://renlifang.msra.cn), and EntityCube (http://entitycube.research.microsoft.com).
