wiki:en/LuQinAbstract2014

Web Persons Disambiguation

By Prof. Qin Lu

Dept. of Computing, HK Polytechnic University

Abstract:

Finding information about person on the Internet is one of the most common activities of online users. Person’s names, however, are highly ambiguous with a large number of people sharing the same name. Web person disambiguation (WPD) is then becoming an important function that a comprehensive search engine should provide. In this talk, we will discuss the challenges in WPD and our solutions to these challenges. Our work leverages on recent advancements in feature extraction (keyword) from a large naturally annotated resource (Wikipedia), to disambiguate names through a hierarchical co-reference model which can make use of semantically more relevant information and extracting profiles using semantic constraints. We further illustrate the effectiveness of our proposed approaches through the comparison to other state-of-the-art works using publicly available datasets on WePs.

Bio:

Prof. Lu is the associate head of Dept. of Computing, Hong Kong Polytechnic University. Her research areas are in natural language processing, computational linguistics, lexical semantics, text mining and knowledge discovery. She is mostly focused on using natural language processing method on information extraction and text mining. She has conducted extensive work on Chinese collocation extraction, terminology extraction, and ontology construction for Chinese text in recent years. Prof. Lu received her B.S. in E.E. from Beijing Normal University, M.S. and Ph.D. in computer science from the University of Illinois at Urbana-Champaign. She is currently the chief editor of IJCPOL.

Last modified 5 years ago Last modified on Sep 23, 2014 10:41:21 AM