A version of the classic Taboo® game
where AI programs guess the names of cities
from simple textual hints.

on 21 August 2017 in Melbourne

NEWS: Results of the challenge HERE.

What is the challenge about?

The Challenge is to develop a computer program capable of guessing the name of a city from simple, increasingly informative textual hints. The winner is the agent that can find the most cities with the least amount of incorrect guesses. In the example below, the Describer (in our case, an automated service) gives a hint in every step, and the Guesser (to be developed by the participants) provides the name of a city that, in principle, matches the set of descriptions provided so far.

                            Guesser: START
Describer: sea  
                            Guesser: Sydney
Describer: no. yearly festival
                            Guesser: Rio de Janeiro
Describer: no. bridges
                            Guesser: Amsterdam
Describer: no. renaissance art  
                            Guesser: Venice
Describer: yes  

The hints provided by the Describer were gathered from online games successfully played by humans, in order to ensure that hints resemble those produced using human intelligence and that the games are solvable. Guesser agents are evaluated over a predefined set of evaluation games.

The GUESSence app

We have developed an Android app that is available for human play of the City Challenge game and was used to gather the human play data for the competition. This app It is available for free download from the Google Play Store. (The app is not required to participate in the competition.)

Who can participate?

The competition is open to everyone: individuals or groups of scientists, students, developers, enthusiasts. We will happily accept submissions pertaining to a diversity of disciplines and approaches; to name a few without being exhaustive:

  • graph search algorithms on knowledge graphs;
  • logical inference over formal knowledge;
  • statistical approaches on textual corpora, e.g., distributional semantics;
  • machine learning methods (e.g., trained on gameplays provided by us);
  • etc.

How can I participate?

For detailed rules and specifications please check out the Taboo Challenge Handbook.
In short:

  1. you register on this website;
  2. you develop your guesser using the programming language and the knowledge resources of your choice, provided that you respect some minimum requirements;
  3. you test your solution with the online describer agent we provide;
  4. you may participate to the preliminary pilot competition if you wish to test your solution in real conditions;
  5. you submit your solution to us, together with a 4-8 page description in the form of a workshop paper, before the deadline.

What are the prizes?

As organiser of the event, the ESSENCE Marie Curie Training Network offers valuable prizes to the authors of the best submissions:

  • a first prize for the winner
  • a prize for the most innovative or scientifically interesting solution: if you think you found an elegant solution but are uncertain of its performance, do not hesitate to make a submission as you may be the best candidate for this prize;
  • financial support for the top submissions to cover travel costs and/or the IJCAI registration fee;
  • for all accepted submissions, a paper published at the Taboo Challenge workshop of the prestigious IJCAI conference.

More details about the prizes will be announced soon.

Important Dates

Registrations open: 1 March 2017.
Submissions to the pilot competition (optional): 1 May 2017 by midnight (BST).
Deadline for submissions: 31 May 2017 by midnight (BST).
Extended to 10 June 2017 by midnight (BST).
Notification: 16 June 2017.
Announcement of results: at the IJCAI workshop, 21 August 2017.


In order to participate you need to register on this website. Registration is really easy and gives you access to the online describer agent (with which you can test your guesser), as well as to a corpus of gameplays by humans that you can use in your code. By registering you also make sure to be regularly updated with news about the competition.


Note that registering here does not engage you in any way to participating to the IJCAI conference or to the Challenge Workshop: the registration process to the workshop is an entirely independent procedure to be carried out from the IJCAI website. We do not set this as a prerequisite to registering here or to submitting a solution. However, participation to the Challenge Workshop at IJCAI is a prerequisite to receiving a prize and also to having the paper describing your submission accepted as an official IJCAI workshop paper.

The IJCAI Workshop

The Taboo Challenge Workshop, hosted at the prestigious IJCAI 2017 Conference on 21 August, will be the closing event of the competition. The programme of the one-day workshop will include:

  • talks by successful participants, demos, and discussion;
  • announcement of the winners and presentation of the awards;
  • a panel discussion on ‘intelligence’ in the context of the various approaches seen at the workshop, inviting high-profile AI researchers attending IJCAI.

More details regarding the workshop can be found here.


The competition is organised by the ESSENCE Marie Curie Training Network. ESSENCE is a four-year, 4M€ project funded by the European Commission, bringing together researchers and practitioners from computer science, artificial intelligence, robotics, natural language processing, linguistics, philosophy, and cognitive science.

Organising Committee

Michael Rovatsos, University of Edinburgh, UK
Gábor Bella, University of Trento, Italy
Dagmar Gromann, CSIC, Barcelona, Spain

Programme Committee

Manuel Atencia, INRIA Grenoble, France
Gábor Bella, University of Trento, Italy
Katrien Beuls, Vrije Universiteit Brussel, Belgium
Aysenur Bilgin, University of Amsterdam, Netherlands
Jérôme Euzenat, INRIA Grenoble, France
Raquel Fernández, University of Amsterdam, Netherlands
Kobi Gal, Ben-Gurion University of the Negev, Israel
Fausto Giunchiglia, University of Trento, Italy
Dagmar Gromann, IIIA-CSIC, Spain
Fiona McNeill, Heriot-Watt University Edinburgh, UK
Roberto Navigli, University of Rome “La Sapienza”, Italy
Nir Oren, University of Aberdeen, UK
Iyad Rahwan, MIT, USA
Michael Rovatsos, University of Edinburgh, UK
Marco Schorlemmer, IIIA-CSIC Barcelona, Spain
Michael Spranger, Sony Computer Science Labs Tokyo, Japan
Remi van Trijp, Sony Computer Science Labs Paris, France

Advisory Board

Marcelo G. Armentano, UNICEN Buenos Aires, Argentina (Social Influence Analysis Contest)
Catholijn Jonker, Delft University of Technology, Netherlands (Automated Negotiating Agents Competition)
Diego Perez-Liebana, University of Essex, UK (General Video Game AI Competition)
Wolf Ketter, Erasmus University Rotterdam, Netherlands (Power Trading Agent Competition)
Gerhard Lakemeyer, RWTH Aachen, Germany (Winograd Schema Challenge)
Jochen Renz, Australian National University, Australia (Angry Birds Competition)
Pavel Shvaiko, University of Trento, Italy (Ontology Alignment Evaluation Initiative)


Should you have any kind of questions, do not hesitate to contact us at If you register we will keep you informed of the latest news about the challenge.

Marie Curie Initial Training Network (2013-2017)