Contact Information

School of Information Management,
Wuhan University,
Wuhan, Hubei Province,
P.R.China. 430072

Lecture Information (July 12)

2019-07-12 09:49:07

Title: Pair-Linking for Collective Entity Disambiguation

Speaker: SUN Aixin, Associate Professor, School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore

Time: 14:30 pm, July 12, 2019

Venue: Lecture Hall 212, School of Information Management

About SUN Aixin

Dr. SUN Aixin is an Associate Professor and Assistant Chair (Admissions and Outreach) with School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore. He received B.A.Sc (1st class honours) and Ph.D. both in Computer Engineering from the same school in 2001 and 2004 respectively. Aixin's research areas include Information Retrieval, Text Mining, Social Computing, and Digital Libraries. Aixin is a member of editorial board for JASIST, member of editorial board for Information Retrieval Journal, and an associate editor for Neurocomputing. He has been a PC member of many major conferences such as SIGIR, WSDM, and WWW.

Lecture Abstract

Mentions of named entities such as people, places, and organizations are commonplace in documents. However, these mentions are usually ambiguous: the same entity may be mentioned in different surface forms, and the same surface form may refer to different named entities. Collective entity disambiguation or collective entity linking aims to jointly resolve multiple mentions by linking them to their associated entities in a knowledge base. Previous works are primarily based on the underlying assumption that entities within the same document are highly related. We challenge this assumption and propose Pair-Linking, a novel iterative solution for collective entity disambiguation. Instead of considering all the given mentions, Pair-Linking iteratively selects a pair with the highest confidence at each step for decision making.