Abstract

Extracting knowledge from Web pages and integrating it into a coherent knowledge base (KB) is a task that spans the areas of natural language processing, information extraction, information integration, databases, search, and machine learning. Recent years have seen significant advances in knowledge base construction, in both academia and industry. Many popular offerings, including digital assistants (Siri, Cortana, and Google Now) as well as search interfaces (Yahoo!, Bing, and Google) leverage semantic understanding and structured knowledge bases to respond to users. A similarly abundant set of knowledge systems have been developed at top universities such as Stanford (DeepDive), Carnegie Mellon (NELL), the University of Washington (OpenIE), the University of Mannheim (DBpedia), and the Max Planck Institut Informatik (YAGO, WebChild) among others. Our workshop serves as a forum for researchers on knowledge base construction in both academia and industry.
Unlike many other workshops, our workshop puts less emphasis on conventional paper submissions and presentations, but focuses on visionary papers and discussions, and structures the program around high-profile keynotes that foster discussion. In addition, one of the workshop’s unique characteristics is its nomadic nature; AKBC has co-located with conferences which serve diverse communities, attesting to the broad appeal of the topic. Following the standalone AKBC 2010, AKBC 2012 (HLT-NAACL), AKBC 2013 (CIKM), and AKBC 2014 (NIPS), have each featured a dozen invited talks, drawn 20-35 submissions, and attracted audiences of 75-100 from NLP …

Date

2016

Authors

Jay Pujara, Tim Rocktäschel, Danqi Chen, Sameer Singh

Conference

Proceedings of the 5th Workshop on Automated Knowledge Base Construction