Cognitum 2016 Call for Papers

Second Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2016)

Held in conjunction with IJCAI 2016
July 11, 2016, 8:30 a.m. – 12:30 p.m.
New York Hilton Midtown Hotel, 1335 Avenue of the Americas, New York NY 10019 USA

Register Now

Several grants (for students and early-stage researchers) to partially subsidize participation in the workshop are available through a sponsorship from the Artificial Intelligence journal (AIJ). Please contact the organizers for more information.


8:40 a.m. Ernest Davis (Professor, Department of Computer Science, Courant Institute of Mathematical Sciences, New York University) will talk about Collecting Commonsense Problems from Text.


Building Complementary Domain Taxonomies using Query Enrichment
Simoni Shah, Shraddha Bhattad, Sanket Lokegaonkar, and Ganesh Ramakrishnan

Critic Networks for Commonsense Problem Solving
Heikki Ruuska

Empirical Knowledge Acquisition of Commonsense Psychology
William Jarrold and Peter Yeh

I’ll know it when I see it: Toward cognitively plausible recommendations
Susan Epstein and Eric Osisek

Lexical Knowledge Acquisition: Towards a Continuous and Flexible Representation of the Lexicon
Pierre Marchal and Thierry Poibeau

Unsupervised Natural Language Acquisition and Grounding to Visual Representations for Robotic Systems
Muhannad Alomari, Paul Duckworth, Yiannis Gatsoulis, David Hogg, and Anthony Cohn


Following the success of the well-attended First Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2015), we are excited to continue this workshop series at IJCAI 2016 in New York in July 2016. The workshop focuses on disseminating work that bridges cognitive psychology and artificial intelligence in an informal setting that promotes lively discussion among the participants.

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, knowledge acquisition should exhibit characteristics akin to those of human learning, so that humans can relate to it and be able to interact with it as if it were a knowledgeable colleague. Thus, we mean “cognitive” in the workshop’s title to characterize both the form of knowledge and the process of its 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 use heavy computational machinery to improve performance at the expense of psychological validity.

Since knowledge acquisition cannot proceed independently of other aspects of cognition, like perception, reasoning, and 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.

As part of this second instantiation of the workshop, we particularly encourage work on the theme Algorithms and Data Structures for Cognitive Knowledge Acquisition at a Massive Scale.


May 2, 2016: Submission deadline
May 23, 2016: Acceptance notification
May 31, 2016: Early registration deadline
June 20, 2016: Final PDF file deadline
July 11, 2016: Workshop in New York from 8:30 a.m. to 12:30 p.m.


Papers must be formatted according to the IJCAI 2016 style guide
and be at most 6 pages long, plus an additional bibliography page.

Submissions (in PDF) are accepted through EasyChair:


Register for Cognitum.
You can register for Cognitum even if you didn’t submit a paper.
You can register for Cognitum without having to register for the main IJCAI conference.
IJCAI workshop access is charged by the day. If you register for Cognitum, you can attend another half-day workshop on the same day for FREE. List of workshops.


Loizos Michael, Open University of Cyprus
Erik T. Mueller, Symbolic AI, LLC


Jason Alonso, Luminoso Technologies, Inc.
Ken Barker, IBM
David Buchanan
Peter Clark, Allen Institute for Artificial Intelligence (AI2)
James Fan
Jonathan Gordon, USC Information Sciences Institute
Hannaneh Hajishirzi, University of Washington
Antonis Kakas, University of Cyprus
Joohyung Lee, Arizona State University
Henry Lieberman, MIT
Rob Miller, University College London
Henry Minsky, Alphabet/Nest Labs
J. William Murdock, IBM
John Prager, IBM
Alessandra Russo, Imperial College London
Claudia Schulz, Imperial College London
Biplav Srivastava, IBM

Sponsored by Artificial Intelligence journal (AIJ)
Sponsored by Artificial Intelligence Journal