In addition to being an original improv comedy show, Improbotics is also the subject of scientific research on the use of artificial intelligence in theatre and on the Turing test*, and it has been presented at international scientific conferences.
- Piotr Mirowski, Kory Mathewson, Boyd Branch, Thomas Winters, Ben Verhoeven (2020) “Rosetta Code: Improv in Any Language”, International Conference on Computational Creativity.
- Gunter Loesel, Piotr Mirowski, Kory Mathewson (2020) “Do Digital Agents Do Dada?”, International Conference on Computational Creativity.
- Piotr Mirowski, Kory Mathewson (2019) “Human Improvised Theatre Augmented with Artificial Intelligence”, AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Atlanta.
- Kory Mathewson and Piotr Mirowski (2018) “Improbotics: Exploring Deception using Machine Intelligence in Improvised Theatre”, AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Edmonton.
- Kory Mathewson and Piotr Mirowski (2017) “Improvised Comedy as a Turing Test“, Creative AI workshop at NIPS – Neural Information Processing Systems, Long Beach. That work featured in the New Scientist (Douglas Heaven, “Robot’s terrible jokes are a new test of machine intelligence”, 16 December 2017).
- Kory Mathewson and Piotr Mirowski (2017) “Improvised theatre alongside artificial intelligences“, AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Snowbird.
Piotr and Kory, who are both improvisers and researchers in AI, believe in an interdisciplinary approach to the arts and sciences, and have created a community of like-minded artists, researchers, drama lecturers and science communicators including Boyd Branch, Sarah Davies, Jenny Elfving, Ben Verhoeven, Jutta Diessl, Thomas Winters or collaborator Gunter Loesel. Our vision is to explore new forms of human theatre through the help of state-of-the-art research in artificial intelligence and robotics, and to highlight what is uniquely human. For us, the skill of theatrical improvisation is one of the highest forms of human intelligence, and by confronting humans to the incongruity of machines on the stage, we can create new opportunities for comedy.
We are planning on continuing writing about the science behind AI-based improv comedy stage partners. The experimental protocol involves a Turing test* that takes place in a theatre, with both the audience members and the performers left to guess who is a human and who is a machine. In order to test scientific hypotheses about the perception of humans vs. machines and to conduct the Turing test, we typically collect anonymized feedback from audience members as well as feedback from volunteer performers who signed consent forms. Participation in the data collection is always be optional and never mandatory. The experimental protocol has been validated by the institutional ethics board of the University of Alberta and University of Kent. Improbotics performers and artistic collaborators are invited to contribute as authors to the paper if they wish, and all artists are always acknowledged.
* To pass the Turing test, a machine (such as an artificial intelligence-based chatbot) needs to display the appearance of human-level intelligence by fooling a human judge into thinking that it is human.
At the heart of our improv show is the piece of technology that Piotr Mirowski and Kory Mathewson have developed over the years, as part of HumanMachine, and consisting in an artificial intelligence-based chatbot, called A.L.Ex.
A.L.Ex, which stands for Artificial Language Experiment (and is also an obscure reference to the clever parrot), is a computer system that can do speech recognition, improvised dialogue and voice synthesis. It is powered by neural network software. The first version was trained on OpenSubtitles (movie dialogue from a hundred thousand movies). We now use OpenAI‘s GPT-2, trained on 40GB of web pages, Google’s Universal Sentence Encoder and DeepMind’s BigGAN. Our theatre software is programmed by Piotr and Kory using open-source components. Despite being state-of-the-art, A.L.Ex is still a weak form of artificial intelligence.
At its core, A.L.Ex is a language model that captures the complex statistics of words. It is trained to produce the most obvious words that follow any context. It illustrates the fundamental principle of improv: always do the most obvious thing.
A.L.Ex runs on a laptop computer. In the case of HumanMachine’s show, A.L.Ex’s stage presence consists in a portable microphone, amplified sound and video projection, and in a robot produced by EZ-Robot, for which we developed custom control software. In the case of stage Improbotics shows, A.L.Ex controls human improvisers by sending them speech synthesized lines of dialogue via headsets and FM radios.