Interest in creating KBs has often been motivated by the desire to support reasoning on information that would otherwise be expressed in noisy free text and spread across multiple documents.  However, distilling knowledge into a restricted KB can lose important semantic diversity and context.  Traditionally a KB has a single hand-designed schema of entity- and relation-types.  In contrast, universal schema operates on the union of many input schemas, including a great diversity of free textual expressions.  However, previous work on universal schema still distills many textual contexts of the relation between an entity pair into a single embedded vector.  In this talk I will introduce universal schema, then describe recent work leading toward (a) having the textual entity- and relation-mentions themselves represent the KB, (b) using universal schema and neural attention models to provide generalization, (c) logical reasoning on top of this text-KB, and (d) future work on reinforcement learning to guide the search for proofs of the answers to queries.

Bio:

Andrew McCallum is a Professor and Director of the Information Extraction and Synthesis Laboratory, as well as Director of Center for Data Science in the College of Information and Computer Science at University of Massachusetts Amherst. He has published over 250 papers in many areas of AI, including natural language processing, machine learning and reinforcement learning; his work has received over 45,000 citations. He obtained his PhD from University of Rochester in 1995 with Dana Ballard and a postdoctoral fellowship from CMU with Tom Mitchell and Sebastian Thrun. In the early 2000's he was Vice President of Research and Development at at WhizBang Labs, a 170-person start-up company that used machine learning for information extraction from the Web. He is a AAAI Fellow, the recipient of the UMass Chancellor's Award for Research and Creative Activity, the UMass NSM Distinguished Research Award, the UMass Lilly Teaching Fellowship, and research awards from Google, IBM, Microsoft, and Yahoo. He was the General Chair for the International Conference on Machine Learning

(ICML) 2012, and is the current President of the International Machine Learning Society, as well as member of the editorial board of the Journal of Machine Learning Research. For the past ten years, McCallum has been active in research on statistical machine learning applied to text, especially information extraction, entity resolution, social network analysis, structured prediction, semi-supervised learning, and deep neural networks for knowledge representation. His work on open peer review can be found at http://openreview.net. McCallum's web page is http://www.cs.umass.edu/~mccallum