Commonsense Reasoning

Commonsense Reasoning ~ Home


Thirteenth International Symposium on Commonsense Reasoning (Commonsense-2017)

We invite you to participate in Commonsense-2017, to be held at the University College London, November 6-8, 2017.

The biennial Commonsense Symposia series provides a forum for exploring one of the long-term goals of Artificial Intelligence, endowing computers with common sense.


November 6-8, 2017.


Commonsense-2017 will take place on the campus of University College London:
Haldane Room
Wilkins Building, Gower Street, London WC1E 6BT


Registration costs for this symposium are £25.00, and must be made via the UCL online store:
Please note that one author from each accepted paper must register by Friday October 6.

Local accommodation

Numerous hotels are within walking distance of UCL. Please see the following suggestions, and contact hotels directly for booking:

Invited speakers

We are happy to announce two invited speakers for Commonsense 2017:
Murray Shanahan, Imperial College London (bio)
Sebastian Riedel, University College London (bio)


Monday November 6

9:30-11:00 Paper Session 1
Vitaliy Batusov and Mikhail Soutchanski. Situation Calculus Semantics for Actual Causality
Christoph Schwering. Reasoning in the Situation Calculus with Limited Belief
Christos Vlassopoulos and Alexander Artikis. Towards A Simple Event Calculus for Run-Time Reasoning
11:00-11:30Coffee break
11:30-13:00Paper Session 2
Piotr Chabierski, Alessandra Russo, Mark Law and Krysia Broda. Machine Comprehension of Text Using Combinatory Categorial Grammar and Answer Set Programs
Daan Apeldoorn and Gabriele Kern-Isberner. An Agent-Based Learning Approach for Finding and Exploiting Heuristics in Unknown Environments
Guillem Collell and Marie-Francine Moens. Acquiring Common Sense Spatial Knowledge through Implicit Spatial Templates
14:30-15:30Keynote: Sebastian Riedel, University College London
title: Reading and Reasoning with Vector Representations
abstract: In recent years, vector representations of knowledge have become popular in NLP and beyond. They have at least two core benefits: reasoning with (low-dimensional) vectors tends to lead to better generalisation, and usually scales very well. But they raise their own set of questions: What type of inferences do they support? How can they capture asymmetry? How can explicit background knowledge be injected into vector-based architectures? How can we provide “proofs” that justify predictions? In this talk, I sketch some initial answers to some of these questions based on our recent work. In particular, I will illustrate how a vector space can simulate the workings of logic.
bio: Sebastian Riedel is a reader in Natural Language Processing and Machine Learning at the University College London (UCL), where he is leading the Machine Reading lab. He is also the head of research at Bloomsbury AI and an Allen Distinguished Investigator. He works in the intersection of Natural Language Processing and Machine Learning, and focuses on teaching machines how to read and reason. He was educated in Hamburg-Harburg (Dipl. Ing) and Edinburgh (MSc., PhD), and worked at the University of Massachusetts Amherst and Tokyo University before joining UCL.
15:30-16:00Coffee break
16:00-17:30Paper Session 3
Toryn Q. Klassen, Hector J. Levesque and Sheila A. McIlraith. Towards Representing What Readers of Fiction Believe
Nikoleta Tsampanaki, Giorgos Flouris and Theodore Patkos. Steps Towards Commonsense-Driven Belief Revision in the Event Calculus
Loizos Michael. The Advice Taker 2.0
17:30-18:00Discussion re. Commonsense-2019 (part A)

Tuesday November 7

9:30-11:00Paper Session 4
Tim Fernando. Predications, fast and slow
Arina Britz and Ivan Varzinczak. Context-based defeasible subsumption for dSROIQ
Haythem Ismail and Patrick Attia. Towards a Logical Analysis of Misleading and Trust Erosion
11:00-11:30Coffee break
11:30-13:00Paper Session 5
Adam Richard-Bollans, Lucía Gómez Álvarez, and Anthony Cohn. The Role of Pragmatics in Solving the Winograd Schema Challenge
Denis Golovin, Jens Claßen, and Christoph Schwering. Reasoning about Conditional Beliefs for the Winograd Schema Challenge
Attila Novák and Borbála Siklósi. A model for high-coverage lexical semantic annotation generation
14:30-15:30Keynote: Murray Shanahan, Imperial College London
title: Naive Physics Revisited
abstract: Pat Hayes’s naïve physics papers were highly influential in the 1980s and 90s, inaugurating the field of qualitative reasoning, inspiring the CYC project, and laying the foundations of the semantic web. Back then, the underlying motive for studying common sense physics was the development of human-level AI. But this grandiose aim slowly faded into the background of mainstream AI research, and has only recently been revived, under the new moniker of artificial general intelligence (AGI). Nowadays, AGI is being pursued through the methodology of neural networks, an approach that was anathama to the logic-oriented common sense reasoning community that arose in the 1980s. In this talk I will examine the importance of common sense physics for contemporary AGI research, highlighting a number of insights from AI’s past that are still relevant today.
bio: Murray Shanahan is Professor of Cognitive at Imperial College London and a Senior Research Scientist at DeepMind. He works on artificial intelligence, neurodynamics, and philosophy of mind. Educated at Imperial College and Cambridge University (King’s College), he became a full professor at Imperial in 2006, and joined DeepMind in 2017. He was scientific advisor to the film Ex Machina, and regularly appears in the media to comment on artificial intelligence and robotics. As well as many scientific papers he has published several books, including “Embodiment and the Inner Life” (Oxford University Press, 2010) and “The Technological Singularity” (MIT Press, 2015).
15:30-16:00Coffee break
16:00-17:30Panel Session: Evaluation of Commonsense Reasoning
José Hernández-Orallo (Universitat Politècnica de València)
Murray Shannahan (Imperial College London)
Leora Morgenstern (Leidos)
Andrew S. Gordon (University of Southern California)
Session chair: Gyorgy Turan (University of Illinois at Chicago)
17:30-18:00Discussion re. Commonsense-2019 (part B)
EveningPlease join us for a group dinner at a local restaurant, location to be determined, at your own expense.

Wednesday November 8

9:00-10:30Paper Session 6
Claudette Cayrol, Jorge Fandinno, Luis Fariñas and Marie-Christine Lagasquie-Schiex. Valid attacks in Argumentation Frameworks with Recursive Attacks
Nourhan Ehab and Haythem Ismail. LogAG: An Algebraic Non-Monotonic Logic for Reasoning with Uncertainty
Theodoros Mitsikas, Nikolaos Spanoudakis, Petros Stefaneas, and Antonis Kakas. From Natural Language to Argumentation and Cognitive Systems
10:30-11:00Coffee break
11:00-12:30Paper Session 7
Amr Dawood and James Delgrande. A Study of Kernel Contraction in EL
Bryan Williams, Henry Lieberman and Patrick Winston. Understanding Stories with Large-Scale Commonsense
Don Perlis, Justin Brody, Sarit Kraus and Michael Miller. The Internal Reasoning of Robots

Call for Papers

Call for Papers
Thirteenth International Symposium on Commonsense Reasoning (Commonsense-2017)

We invite submissions to Commonsense-2017, to be held in London at the University College London, November 6-8, 2017.

Endowing computers with common sense is one of the major long-term goals of Artificial Intelligence research. Commonsense knowledge and reasoning are relevant for many applications of current interest. Examples include robot and human collaboration, transparent machine-learning systems that can explain their conclusions, social media and story understanding software, and dialogue systems. The recent resurgence of interest in commonsense reasoning reflects a wider societal reaction to current technological advances, such as the fact that “next year a law will come into operation in [EU] member states which gives everyone a right to an explanation of any decision affecting them that has been reached algorithmically” [Guardian newspaper, 14 April 2017].

Approaches to acquiring commonsense knowledge and performing commonsense reasoning may incorporate semantics-based representation and inference, machine learning, natural language processing, computer vision, and/or cognitive science. The symposium aims to encourage cross-fertilization between these and other techniques. The synthesis of multiple approaches is challenging, but could jump-start progress on many outstanding problems of commonsense reasoning.

We welcome a wide variety of submissions, including formal results, experimental results, demos, surveys, evaluations and comparisons of different approaches, and papers on methodological issues. While mathematical logic has traditionally been the primary lingua franca of the Symposium, we welcome all relevant and rigorous approaches to automating commonsense knowledge and reasoning.

Topics of interest include, but are not limited to:

  • Semantics-based representations for specific commonsense domains, such as:
    - Time, change, action, causality
    - Commonsense physical and spatial reasoning
    - Legal, biological, medical, and other scientific reasoning incorporating elements of common sense
    - Mental states such as beliefs, intentions, and emotions
    - Social activities and relationships
  • Inference methods for commonsense reasoning, such as:
    - Logic programming
    - Probabilistic, heuristic, and approximate reasoning
    - Nonmonotonic reasoning, belief revision and argumentation
    - Abductive and inductive reasoning
    - Textual Entailment
  • Methods for creating commonsense knowledge bases, such as:
    - Statistical and corpus-based techniques, including both traditional machine learning and deep learning
    - Crowdsourcing
    - Hand-crafting domain theories
    - Hybrid methods
  • Applications of commonsense reasoning, especially interdisciplinary research in the following areas:
    - Natural language understanding (understanding discourse, question answering, semantic parsing)
    - Image understanding
    - Cognitive robotics and planning
    - Web-based applications (search, internet of things)
    - Support technologies (computer-aided instruction, home automation)
  • Discussions of the science of commonsense reasoning research, including:
    - Meta-theorems about commonsense theories and techniques
    - Relation to other fields, such as philosophy, linguistics, cognitive psychology, game theory, and economics
    - Challenge problem sets and benchmarking

By default accepted papers will be published shortly after the symposium in the CEUR Workshop Proceedings series. Authors may however opt out of publishing in CEUR, e.g. if they wish to publish their paper at another venue. All accepted papers will be made available on the website for the duration of the symposium. A special issue of Annals of Mathematics and Artificial Intelligence, which will include selected and extended papers from Commonsense-2017, is currently planned; journal submissions will be due in winter 2018.

Important Dates

- Submissions due: Extended to Tuesday, August 8, 2017
- Submission notification date: September 8, 2017
- Camera-ready versions due: Extended to October 20, 2017
- Symposium: November 6-8, 2017


- Submissions will be made through EasyChair, at:
- Papers are limited to 6 pages, prepared in IJCAI or AAAI format, using Letter or A4 sized paper, plus one additional page for references.

Review Process

Each paper will receive three blind peer reviews. Selection criteria include novelty, technical accuracy and rigor, significance and generalizability, relevance, and quality of writing. Anonymization of papers is not required.

Invited Speakers

We are happy to announce two invited speakers for Commonsense 2017:
Murray Shanahan, Imperial College London (bio)
Sebastian Riedel, University College London (bio)

Conference Chairs

Andrew S. Gordon, University of Southern California
Rob Miller, University College London
Gyorgy Turan, University of Illinois at Chicago and University of Szeged

Program Committee

Eyal Amir, University of Illinois at Urbana-Champaign
Chitta Baral, Arizona State University
Vaishak Belle, University of Edinburgh
Brandon Bennett, University of Leeds
Gábor Berend, University of Szeged
Nicola Bicocchi, Unversity of New Brunswick
Antonis Bikakis, University College London
Bert Bredeweg, University of Amsterdam
Erik Cambria, Nanyang Technological University
Cungen Cao, Chinese Academy of Sciences
Nathanael Chambers, United States Naval Academy
William Cohen, Carnegie Mellon University
Tony Cohn, University of Leeds
Ernest Davis, New York University
Gerard de Melo, Rutgers University
Valeria De Paiva, University of Birmingham
Luke Dickens, University College London
Esra Erdem, Sabanci University
Nina Gierasimczuk, Technical University of Denmark
Jonathan Gordon, USC Information Sciences Institute
Catherine Havasi, Luminoso Technologies
Jose Hernandez-Orallo, Universitat Politecnica de Valencia
Jeff Horty, University of Maryland
Daniela Inclezan, Miami University
Naoya Inoue, Tohoku University
Benjamin Johnston, University of Technology Sydney
Antonis Kakas, University of Cyprus
Gerhard Lakemeyer, RWTH Aachen University
Henry Lieberman, Massachusetts Institute of Technology
Vladimir Lifschitz, University of Texas
Fangzhen Lin, Hong Kong University of Science and Technology
Quan Liu, University of Science and Technology of China
Loizos Michael, Open University of Cyprus
Niloofar Montazeri, University of California Riverside
Leora Morgenstern, Leidos
Charlie Ortiz, Nuance Communications
Sebastian Pado, Stuttgart University
Theodore Patkos, Institute of Computer Science, FORTH
Pavlos Peppas, University of Patras
Dimitris Plexousakis, Institute of Computer Science, FORTH
Alan Ritter, Ohio State University
Chiaki Sakama, Wakayama University
Steven Schockaert, Cardiff University
Bob Sloan, University of Illinois at Chicago
Mark Steedman, University of Edinburgh
Michael Thielscher, University of New South Wales
Richmond Thomason, University of Michigan
Lucy Vanderwende, Microsoft Research
Laure Vieu, Institut de Recherche en Informatique de Toulouse
Stefan Woltran, Technische Universität Wien


For questions or comments about please email

Website design by Benjamin Johnston, based on the Fluid 960 Grid System by Stephen Bau and Nathan Smith. Crowd photo by James Cridland.