Research Statement

I'm Anthony Francis, an artificial intelligence researcher currently working for Google's Search Quality department. I design intelligent machines and emotional robots, focusing on contextual memory: how implicit context helps us retrieve and use information more appropriately.

Over the course of our lives we learn thousands or millions of facts, most of which are irrelevant to our current situation. Even when we can clearly specify the information we need, there may be many facts that fit the criteria, and it would be most efficient to consider the most relevant facts first.

Fortunately, the situations we are in often contain enough information to appropriately rank the facts we know in the most appropriate order - if we collect information about the situation in a context, and structure memory retrieval to take advantage of that context. My work on context sensitive asynchronous memory explores this idea as applied to information retrieval and case-based planning.

This can include not just memory for facts, but memory for emotion: annotating experiences with the emotions they cause can be used to learn emotional responses that are appropriate for different situations. My work on emotional long term memory explores this idea as applied to robotic control and game artificial intelligence.

In addition to my primary focus on memory in reasoning and emotion, my other research interests include programming language design, interactive fiction, natural language understanding, animal cognition, cognitive science, intelligent agents, and physics, particularly general relativity. For more information:

Contextual Memory for Information Retrieval

My doctoral work focused on how understanding context in human memory could improve intelligent information retrieval in machines:
Context Sensitive Asynchronous Memory
I received my Ph.D. in Artificial Intelligence from the College of Computing of the Georgia Institute of Technology in 2000.

While at Tech my research focused on context and its influence on memory, reasoning and behavior.

  • Thesis Proposal (HTML)
  • Dissertation (PDF)
My thesis committee was:
  • Dr. Ashwin Ram (computer science)
  • Dr. Janet Kolodner (computer science)
  • Dr. Kurt Eiselt (computer science)
  • Dr. Ashok Goel (computer science)
  • Dr. Nancy Nersessian (computer science, psychology, philosophy)
I conducted information retrieval research related to my doctoral work jointly at Georgia Tech and at Enkia Corporation, which was reported in the following publications:

Contextual Memory for Emotional Agents

In a joint project with Georgia Tech and Yamaha Motor Corporation, I studied how emotional long term memory could improve the believability and ease the design of the construction of a robot pet. A publication on this is in press.

Research Projects

I have published papers in the AAAI Workshop on Case-Based Reasoning, the Knowledge Compilation and Speedup Learning Workshop, and the European Conference on Machine Learning.

Research Groups

While at Georgia Tech, I participated in several research groups, including the IGOR Group, the NLR Group, the Creativity Group, and, of course, the AI and Cognitive Science Groups.
  • The IGOR Group Research in learning, case-based reasoning, natural language understanding, creativity, education, and cognitive science.
  • The NLR group An interdisciplinary research group investigating natural language issues.
  • Artificial Intelligence Group The College of Computing's Artificial Intelligence program.
  • Cognitive Science Group The interdisciplinary Cognitive Science program at Georgia Tech.
I have also worked at CMU, SRI, Yamaha, and Enkia Corporation.