IJCAI 2015 Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2015)
Call for Papers
The first Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2015) will be held at IJCAI 2015 in July 2015 in Buenos Aires, Argentina.
- Lenhart Schubert, What kinds of knowledge are needed for genuine understanding?, Professor, Department of Computer Science, University of Rochester VIDEO
- Milind Tambe, Green security games, Helen N. and Emmett H. Jones Professor in Engineering, University of Southern California
Cognitive systems are able to learn and reason in a manner that facilitates their natural and fruitful interaction with humans. Ultimately, this interaction aims to extend and enhance human cognition, not by having cognitive systems operate as subsidiary workers that solve problems for humans, but by having cognitive systems act as expert assistants able to collaborate with humans and provide them with advice in a form compatible with how humans naturally process and understand information.
Knowledge acquisition is central to the design of such cognitive systems. Knowledge should be representable in a form understandable by humans, e.g., as simple arguments represented in high-level symbolic or statistical expressions. At the same time, the process of acquisition itself should exhibit characteristics akin to those of human learning, so that humans can relate to it and be able to interact with it as advice coming from a knowledgeable colleague. Thus, we mean “cognitive” in the workshop’s title to be interpreted as characterizing both the form of “knowledge” and the process of “acquisition”.
Unlike the significant body of work on mining the web for facts or answers to specific questions (e.g., NELL, IBM’s Watson system for Jeopardy!), the workshop’s emphasis is on the acquisition of general inference rules that can be applied by a cognitive system in novel situations to elaborate what has been sensed with plausible and useful inferences. Along with computational efficiency, scalability, autonomy, and formal analysis of the process, key is also the use of naturalistic algorithms. We are more interested in contributions that propose acquisition processes that could potentially err more (when typical humans would also err), but are simple and intuitive, rather than acquisition processes that employ heavy computational machinery to improve performance at the expense of psychological validity.
Since knowledge acquisition cannot proceed independently of other aspects of cognition, such as perception and reasoning / decision making, we also welcome contributions on other aspects of cognition, as long as they are directly tied to knowledge acquisition within a unified framework. We particularly encourage the demonstration of (prototype) cognitive systems that implement the proposed frameworks, and discuss solutions to pragmatic concerns that had to be addressed.
We welcome ongoing and exciting preliminary work. Topics of interest include, but are not limited to:
- Formal frameworks for acquiring cognitive knowledge.
- Principled evaluation of acquired cognitive knowledge.
- Psychologically‐guided design of the acquisition process.
- Considerations related to scalability and parallelization.
- Active choice among available learning data / resources.
- Representation languages for cognitive knowledge.
- Static versus temporal / causal cognitive knowledge.
- Interaction of acquisition with perception and reasoning.
- Alternative acquisition methods (e.g., crowdsourcing).
- Acquisition from media other than text (e.g., video).
- Architecture and implementation of cognitive systems.
- Real‐world applications that utilize cognitive knowledge.
May 15, 2015: Submission deadline
June 1, 2015: Acceptance notification
June 19, 2015: Early registration deadline
June 21, 2015: Final PDF file deadline
July 25, 2015: Cognitum 2015 workshop
Papers must be formatted according to the IJCAI 2015 style guide
and be at most 6 pages long, plus an additional bibliography page.
Submissions (in PDF) are accepted through EasyChair:
A number of travel grants (for students and early-stage researchers) to partially subsidize participation in the workshop will be available through a sponsorship from the Artificial Intelligence journal.
David Buchanan, IBM Watson Group and IBM Research
Peter Clark, Allen Institute for Artificial Intelligence
Paul Compton, University of New South Wales
Jonathan Gordon, University of Southern California / Information Sciences Institute
Aditya Kalyanpur, Bridgewater Associates
Pat Langley, Carnegie Mellon University, Institute for the Study of Learning and Expertise
Henry Minsky, Nest Labs / Google
N.S. Narayanaswamy, Indian Institute of Technology Madras
Massimo Poesio, University of Essex
Rosario A. Uceda-Sosa, IBM Research