Topic：Knowledge Base Population: Looking Back and Looking Ahead

Time：2014年12月12日（周五）上午 9:30 - 10:30

Venue：信电大楼-215学术厅

Speaker：Heng Ji, Associate Professor,

          Rensselaer Polytechnic Institute

Abstract

The main goal of the Knowledge Base Population (KBP) is to gather information about an entity that is scattered among the documents of a large collection, and then use the extracted information to populate an existing knowledge base. In this talk I will present the evolutionary path of the problems and advances in the past five years, as well as the overview of current problems and potential solutions. Compared to traditional Information Extraction, using multiple information sources and systems for KBP is beneficial due to multi-source/system consolidation and challenging due to the resulting inconsistency and redundancy. I will focus on presenting two novel approaches: (1) Collective inference for Entity Linking based on Abstract Meaning Representation; and (2) An unsupervised multi-dimensional truth finding framework which incorporates signals from multiple sources, multiple systems and multiple pieces of evidence by knowledge network construction through multi-layer deep linguistic analysis.

Biography

Heng Ji is Edward P. Hamilton Development Chair Associate Professor in Computer Science Department of Rensselaer Polytechnic Institute. She received her B.A. and M. A. in Computational Linguistics from Tsinghua University in 2000 and 2002 respectively, and her M.S. and Ph.D. in Computer Science from New York University in 2005 and 2007 respectively. Her research interests focus on Natural Language Processing and its connections with Data Mining, Network Science, Social Cognitive Science, Security and Vision. She received Google Research Awards in 2009 and 2014, NSF CAREER award in 2009, Sloan Junior Faculty Award in 2012, IBM Watson Faculty Award in 2012 and 2014, PACLIC2012 Best Paper Runner-up, "Best of SDM2013" paper, "Best of ICDM2013" paper and "AI's 10 to Watch" Award by IEEE Intelligent Systems in 2013. She is the leader of the U.S. ARL projects on information fusion and knowledge networks construction. She coordinated the NIST TAC Knowledge Base Population task in 2010, 2011, 2014 and 2015, served as the vice Program Committee Chair for IEEE/WIC/ACM WI2013,  the Information Extraction area chair for NAACL2012, ACL2013, EMNLP2013 and NLPCC2014, Content Analysis Track Chair of WWW2015, and the Financial Chair of IJCAI2016. Her research is funded by the U.S. NSF, ARL, DARPA, AFRL, Google, Disney, IBM and Bosch.