Institute of Information Science, Academia Sinica

Learning to reason and understand the world’s knowledge is a fundamental problem in Artificial Intelligence (AI). While it is always hypothesized that both the symbolic and statistical approaches are necessary to tackle complex problems in AI, in practice, bridging the two in a combined framework might bring intractability—most probabilistic first-order logics are simply not efficient enough for real-world sized tasks. In this talk, I will describe some of my recent progress on theories and practices in statistical relational learning: 1) a scalable learning and reasoning framework called ProPPR, whose inference time does not depend on the size of knowledge graphs; 2) a meta-reasoning theory that learns structures from relational data; 3) and a joint approach for scalable information extraction and relational reasoning. This is joint work with William Cohen and Katie Mazaitis.

William Wang (@王威廉) is a final-year PhD student at the Language Technologies Institute (LTI) of the School of Computer Science, Carnegie Mellon University. He works with William Cohen on designing scalable learning and inference algorithms for statistical relational learning, knowledge reasoning, and information extraction. He has published about 30 papers at leading conferences and journals including ACL, EMNLP, NAACL, IJCAI, CIKM, COLING, SIGDIAL, IJCNLP, INTERSPEECH, ICASSP, ASRU, SLT, Machine Learning, and Computer Speech & Language. He receives best paper awards (or nominations) at ASRU 2013, CIKM 2013, EMNLP 2015, and FLAIRS 2011, a best reviewer award at NAACL 2015, the Richard King Mellon Presidential Fellowship in 2011, and he is a Facebook Fellowship finalist for 2014-2015 and 2015-2016. He is an alumnus of Columbia University, and a former research scientist intern of Yahoo! Labs, Microsoft Research Redmond, and University of Southern California. In addition to research, William enjoys writing scientific articles that impact the broader online community: his microblog has more than 2,000,000 views each month.