Cognitum 2018 Call for Papers

Fourth Workshop on Cognitive Knowledge Acquisition and Applications
(Cognitum 2018)

Acquire knowledge from text, reason in novel situations, and offer explanations in a Banking Question Answering and Reasoning shared task.

THANK YOU SPONSORS!

Following the success of the well-attended First, Second, and Third Cognitum workshops at IJCAI, we are excited to continue this workshop series at NAACL-HLT 2018 in New Orleans, Louisiana. The Fourth Cognitum will focus on the integration of natural language processing and knowledge representation and reasoning, which has proved to be a particularly thorny problem. We solicit papers on this problem as well as participants in a shared task involving knowledge acquisition from text and answering and explaining the answers to natural language banking questions that require reasoning to answer.

KEYNOTE SPEAKER: Peter Clark, Allen Institute for Artificial Intelligence

To facilitate natural and fruitful interaction with humans, cognitive systems must be able to learn, reason, and communicate in natural language. 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 help 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 in a form that allows cognitive systems to understand natural language questions, perform reasoning to answer questions, and explain their reasoning. Unlike the significant body of work on mining the web for facts or answers to specific questions (such as NELL and IBM’s Watson Jeopardy! system), the workshop’s emphasis is on the acquisition of general knowledge that can be applied by cognitive systems in novel situations to perform reasoning. At the same time, acquired knowledge should be cognitive knowledge, which exhibits characteristics similar to human knowledge and allows systems to explain their reasoning.

We welcome ongoing and exciting preliminary work. Topics of interest include, but are not limited to:

  • Integrating natural language processing with knowledge representation and reasoning.
  • Acquiring cognitive knowledge (knowledge in a form that supports explanation to humans).
  • Formal frameworks for acquiring cognitive knowledge.
  • Deep learning 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 natural language processing, perception, and reasoning.
  • Alternative acquisition methods (such as crowdsourcing).
  • Acquisition from media other than text (such as video).
  • Architecture and implementation of cognitive systems.
  • Real-world applications that utilize cognitive knowledge.

SHARED TASK

TBD

IMPORTANT DATES

June 5 or 6, 2018: Workshop in New Orleans, Louisiana, USA.

SUBMISSION

TBD

ORGANIZERS

Loizos Michael, Open University of Cyprus
Erik T. Mueller, Capital One

PROGRAM COMMITTEE

Jason Alonso, Luminoso Technologies, Inc.
Ken Barker, IBM
Ernest Davis, New York University
James Fan, HelloVera.ai
Jonathan Gordon, USC Information Sciences Institute
Antonis Kakas, University of Cyprus
Zachary Kulis, Capital One
Margaret Mayer, Capital One
Rob Miller, University College London
J. William Murdock, IBM
Katerina Pastra, Cognitive Systems Research Institute
John Prager, IBM
Alessandra Russo, Imperial College London
Claudia Schulz, TU Darmstadt
Biplav Srivastava, IBM

Cognitum 2017 Program/Proceedings

IJCAI 2017
W12: Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2017)
Room 80.04.22, RMIT University Building 80 (SAB or Swanston Academic Building), 445 Swanston Street, Melbourne, Victoria, 3000

Registration

Program – Sunday August 20, 2017

10:00 Coffee break

12:30 p.m. Lunch break*

Deep Learning and Cognition

  • 2:30 p.m. Masataro Asai and Alex Fukunaga – Classical Planning in Deep Latent Space: From Unlabeled Images to PDDL (and Back)
  • 3:00 p.m. Panel discussion – Can Deep Learning Scale up to High-Level Cognition (generating explanations, arguing for or against a position, understanding stories, planning and scheduling a project, thinking about thinking, and so on)? – Anthony G. Cohn, Mary-Anne Williams, Antonio Lieto

4:00 p.m. Coffee break

* Note that lunch will not be provided.

Cognitum 2017 Call for Papers

Following the success of the well-attended First and Second Workshops on Cognitive Knowledge Acquisition and Applications, we are excited to continue this workshop series at IJCAI 2017 in Melbourne, Australia. This workshop focuses on disseminating work that bridges cognitive psychology and artificial intelligence in an informal setting that promotes lively discussion and community-building among the participants.

KEYNOTE SPEAKERMary-Anne Williams, University of Technology Sydney

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 in a form that allows systems to explain their inferences and accept user feedback. 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.

Knowledge acquisition is central to the design of such cognitive systems. 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 knowledge that can be applied by a cognitive system in novel situations to elaborate what has been sensed with plausible and useful inferences. At the same time, the process of knowledge acquisition should exhibit characteristics akin to those of human learning, allowing the cognitive systems to explain their inferences and accept user feedback to improve their performance.  We are interested in contributions that take a position and discuss the merits of simple and intuitive acquisition processes that could potentially err more (when typical humans would also err) versus the merits of acquisition processes that use computationally-heavy 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.
  • Deep learning 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 third instantiation of the workshop, we particularly encourage work on the theme:

Intelligent Assistants: Explaining Inferences and Accepting User Feedback

IMPORTANT DATES

May 27, 2017: Submission deadline
June 17, 2017: Acceptance notification
July 18, 2017: Final PDF file deadline
August 20, 2017: Workshop in Melbourne, Australia.

SUBMISSION

Papers must be formatted according to the IJCAI 2017 guidelines (http://ijcai-17.org/FormattingGuidelinesIJCAI-17.zip), and be at most 6 pages long, plus an additional bibliography page.

Submissions (in PDF) are accepted through EasyChair:
https://easychair.org/conferences/?conf=cognitum2017

ORGANIZERS

Loizos Michael, Open University of Cyprus
Erik T. Mueller, Capital One

PROGRAM COMMITTEE

David Buchanan, Elemental Cognition/Bridgewater Associates
Ernest Davis, New York University
James Fan, customerserviceai.com
Hannaneh Hajishirzi, University of Washington
Antonis Kakas, University of Cyprus
Zachary Kulis, Capital One
Joohyung Lee, Arizona State University
Rob Miller, University College London
Henry Minsky, Google/Nest Labs
J. William Murdock, IBM
Ravi Palla, Capital One
John Prager, IBM
Alessandra Russo, Imperial College London
Claudia Schulz, Imperial College London
Biplav Srivastava, IBM
Gyorgy Turan, University of Illinois at Chicago

Cognitum 2016 Proceedings

WORKSHOP HIGHLIGHTS

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

Ernest Davis. Collecting Commonsense Problems from Text. SLIDES

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

William Jarrold and Peter Yeh. Empirical Knowledge Acquisition of Commonsense Psychology.

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

Heikki Ruuska. Critic Networks for Commonsense Problem Solving. SLIDES

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

Cognitum 2016 Program

IJCAI 2016
W38: Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2016)
New York Hilton Midtown Hotel, 1335 Avenue of the Americas, New York NY 10019 USA

Program – Monday July 11, 2016

08:30 a.m. Introduction

08:40 a.m. Keynote talk – Collecting Commonsense Problems from Text
Ernest Davis

09:25 a.m. Empirical Knowledge Acquisition of Commonsense Psychology
William Jarrold and Peter Yeh

09:45 a.m. Unsupervised Natural Language Acquisition and Grounding to Visual Representations for Robotic Systems
Muhannad Alomari, Paul Duckworth, Yiannis Gatsoulis, David Hogg, and Anthony Cohn

10:05 a.m. I’ll know it when I see it: Toward cognitively plausible recommendations
Susan Epstein and Eric Osisek

10:25 a.m. Summary

10:30 a.m. Coffee break

11:00 a.m. Critic Networks for Commonsense Problem Solving
Heikki Ruuska

11:20 a.m. Building Complementary Domain Taxonomies using Query Enrichment
Simoni Shah, Shraddha Bhattad, Sanket Lokegaonkar, and Ganesh Ramakrishnan

11:40 a.m. Lexical Knowledge Acquisition: Towards a Continuous and Flexible Representation of the Lexicon
Pierre Marchal and Thierry Poibeau

12:00 p.m. Discussion

12:20 p.m. Concluding thoughts

12:30 Lunch break

Workshop sponsored by Artificial Intelligence journal (AIJ)

Cognitum 2016 Call for Papers

skyline-14619-512
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
Website: http://cognitum.ws/

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.

KEYNOTE TALK

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.

ACCEPTED PAPERS

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

WORKSHOP DESCRIPTION

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.

IMPORTANT DATES

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.

SUBMISSION

Papers must be formatted according to the IJCAI 2016 style guide
(http://ijcai-16.org/downloads/FormattingGuidelinesIJCAI-16.zip),
and be at most 6 pages long, plus an additional bibliography page.

Submissions (in PDF) are accepted through EasyChair:
https://easychair.org/conferences/?conf=cognitum2016

REGISTRATION

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.

ORGANIZERS

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

PROGRAM COMMITTEE

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

Cognitum 2015 Proceedings

César Aguilar and Olga Acosta. Identification of hyponyms, hyperonyms, meronyms, and holonyms in medical texts: A cognitive approach. SLIDES

Fei Fang, Thanh Nguyen, Benjamin Ford, Nicole Sintov, and Milind Tambe. Introduction to green security games (extended abstract).

Zhiye Fei, Daniel Khashabi, Haoruo Peng, and Dan Roth. ILLINOIS-PROFILER: Knowledge schemas at scale. SLIDES

Brendan Juba. Learning abductive reasoning using random examples. SLIDES

Ana-Maria Olteteanu. Towards comparable cognitive creative systems. Two case studies and a general approach based on cognitive processing, knowledge acquisition, and evaluation with human creativity tests. SLIDES

Rafal Rzepka, Kenji Araki, and Marek Krawczyk. Replacing sensors with text occurrences for commonsense knowledge acquisition.

Rafal Rzepka and Kenji Araki. Toward artificial ethical learners that could also teach you how to be a moral man.

Lenhart Schubert, What kinds of knowledge are needed for genuine understanding? VIDEO AUDIO SLIDES

Eduardo Veas and Cecilia di Sciascio. Interactive topic analysis with visual analytics and recommender systems.

Cognitum 2015 Program

Program – Saturday, July 25, 2015

08:00-8:45 Registration

08:45-10:30 Morning session part 1
5 min introduction
30 min paper presentation (including questions): Brendan Juba. Learning abductive reasoning using random examples
30 min paper presentation: Rafal Rzepka, Kenji Araki, and Marek Krawczyk. Replacing sensors with text occurrences for commonsense knowledge acquisition
30 min paper presentation: TBD

10:30-11:00 Coffee break

11:00-12:45 Morning session part 2
5 min introduction
40 min keynote talk: Milind Tambe, Green security games
30 min paper presentation: Eduardo Veas and Cecilia di Sciascio. Interactive topic analysis with visual analytics and recommender systems
30 min paper presentation: Rafal Rzepka and Kenji Araki. Toward artificial ethical learners that could also teach you how to be a moral man

12:45-13:45 Lunch

13:45-15:30 Afternoon session part 1
40 min keynote talk: Lenhart Schubert, What kinds of knowledge are needed for genuine understanding?
30 min paper presentation: César Aguilar and Olga Acosta. Identification of hyponyms, hyperonyms, meronyms,  and holonyms in medical texts

40 min demo session

15:30-16:00 Coffee break

16:00-17:45 Afternoon session part 2
30 min paper presentation: Zhiye Fei, Daniel Khashabi, Haoruo Peng, and Dan Roth. ILLINOIS-PROFILER: Knowledge schemas at scale
30 min paper presentation: Ana-Maria Olteteanu. Towards comparable cognitive creative systems
40 min panel discussion
5 min closing