Learning Knowledge Bases for Text and Multimedia


Lexing Xie, The Australian National University
Haixun Wang, Google Research
ACM Multimedia 2014 Tutorial, Movember 3, 2014

Part I: Leanring knowledge bases from text (download pdf, 16MB),
Part II: Knowledge graphs for images and multimedia (download pdf, 40 MB).
Knowledge acquisition, representation, and reasoning has been one of the long-standing challenges in artificial intelli- gence and related application areas. Only in the past few years, massive amounts of structured and semi-structured data that directly or indirectly encode human knowledge be- came widely available, turning the knowledge representation problems into a computational grand challenge with feasible solutions in sight. The research and development on knowl- edge bases is becoming a lively fusion area among web in- formation extraction, machine learning, databases and infor- mation retrieval, with knowledge over images and multime- dia emerging as another new frontier of representation and acquisition. This tutorial aims to present a gentle overview of knowledge bases on text and multimedia, including rep- resentation, acquisition, and inference. The content of this tutorial are intended for surveying the field, as well as for educating practitioners and aspiring researchers.

This tutorial is structured in two main parts. The first part introduces the background and foundations of knowledge bases, and focuses on knowledge acquisition from text and hyper-text data, the second part discusses ac- quiring and applying knowledge for image and multimedia collections. Tutorial materials and an an- notated bibliography will be released online.

November 2014
Contact: Lexing Xie