Keynote Speakers

Dr. Robert Sanderson

Dr. Robert Sanderson is the Semantic Architect for the J Paul Getty Trust, with responsibility for the design and direction of cultural heritage data information systems spanning the Museum, Research Institute, Conservation Institute and Foundation. His main goal is to find the right balance between ease of publication and consumption of data, and the precision of the data’s semantics. He is one of the driving forces behind, a community of memory organizations focused on using Linked Open Data to describe cultural heritage objects in a usable, useful way. He is chair of the JSON-LD work in the W3C and proposed chair for the W3C Art & Culture community group, is a specification editor and community leader in the IIIF community (, and on the advisory boards of many projects in the cultural sector including the American Art Collaborative and Annotating All Knowledge projects. In his previous position as Standards Advocate at Stanford University, he was involved in the BibFrame ontology with the Library of Congress and many semantic digital library projects. He has also been a Research Scientist at Los Alamos National Laboratory, and a lecturer in Computer Science at the University of Liverpool.


The problem with getting a lot of very smart people in a room to solve a problem is that the solution may only be implementable by organizations with a lot of very smart people. A solution that is too specific and too complete can only be used to solve that one problem, at great expense. There is no room for adopters to solve their own problems, nor to contribute to the solution.

Many digital cultural heritage solutions intended for broad usage have fallen into this trap, and seen minimal adoption despite extensive funding and dedicated effort. Instead of more and more specific solutions, general frameworks that allow adopters to customize their use and adapt over time to evolving best practices have been significantly more successful. The focus should be the on the utility and usability of the framework in which problems can be solved, by non-specialists that have actual problems backed by real content.

The only digital cultural heritage context in which "Build it and they will come" is true is when "it" is a community. A good enough end-to-end solution, with the social support to assist with and encourage adoption, has generated far greater levels of interoperability and exchange of data.

In this keynote, Dr. Sanderson will speak to these topics using as example the evolution of the Semantic Web through Linked Open Data and now towards Linked Open Usable Data, or LOUD. Relevant communities include JSON-LD, IIIF,, Open Annotation and the Google-backed The emphasis will be on the challenge of finding the right balance of functionality versus ease of adoption, and of processes that encourage broad participation but do neither get mired in discussions nor require the constant attention of experts to keep up.

Craig Knoblock, USC Information Sciences Institute

Craig Knoblock is a Research Professor of both Computer Science and Spatial Sciences at the University of Southern California (USC), Director of the Artificial Intelligence Division at the Information Sciences Institute, Research Director of the Center on Knowledge Graphs, and Associate Director of the Informatics Program at USC. He received his Bachelor of Science degree from Syracuse University and his Master’s and Ph.D. from Carnegie Mellon University in computer science. His research focuses on techniques for describing, acquiring, and exploiting the semantics of data. He has published more than 300 journal articles, book chapters, and conference papers on these topics. Dr. Knoblock is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Fellow of the Association of Computing Machinery (ACM), past President and Trustee of the International Joint Conference on Artificial Intelligence (IJCAI), and winner of the 2014 Robert S. Engelmore Award.


Over the last few years we have been mining data from various web sources to create applications that address a variety of real-world challenges, including combating human trafficking, identifying illegal arms sales, and predicting cyber attacks. In one application, we developed a system that aggregates data from online web ads to provide a tool for law enforcement agencies to find and prosecute human traffickers. In a second application, we mine data from a combination of the deep and dark web to identify patterns in the data to make predictions about likely targets of cyber attacks. And in a third application, as part of the American Art Collaborative, we developed the technology to build linked data from the data of 14 museums to create integrated applications about artwork, such as building virtual museums.

In this talk I will describe these applications, the underlying technologies used to build them, and how these same technologies could be used to combat the illicit trade in cultural heritage objects. For example, the same tools for creating linked data about artwork could be used to create an integrated set of linked data about stolen cultural heritage objects, making it easier to identify and return stolen objects. Similarly, the tools for mining the dark web for predicting cyber attacks could be used to identify and track the illicit trade in cultural heritage objects that is occurring in the dark web. And, the combination of linked data and blockchain technologies could be used to track the sale of objects and provide guarantees about the provenance of a given object to avoid later surprises.

More to be announced later.