Improvised Theatre Alongside Artificial Intelligences
Open accessAbstract
This study presents the first report of Artificial Improvisation, or improvisational theatre performed live, on-stage, alongside an artificial intelligence-based improvisational performer. The Artificial Improvisor is a form of artificial conversational agent, or chatbot, focused on open domain dialogue and collaborative narrative generation. Using state-of-the-art machine learning techniques spanning from natural language processing and speech recognition to reinforcement and deep learning, these chatbots have become more lifelike and harder to discern from humans. Recent work in conversational agents has been focused on goal-directed dialogue focused on closed domains such as appointment setting, bank information requests, question-answering, and movie discussion. Natural human conversations are seldom limited in scope and jump from topic to topic, they are laced with metaphor and subtext and face-to-face communication is supplemented with non-verbal cues. Live improvised performance takes natural conversation one step further with multiple actors performing in front of an audience. In improvisation the topic of the conversation is often given by the audience several times during the performance. These suggestions inspire actors to perform novel, unique, and engaging scenes. During each scene, actors must make rapid fire decisions to collaboratively generate coherent narratives. We have embarked on a journey to perform live improvised comedy alongside artificial intelligence systems. We introduce Pyggy and A.L.Ex. (Artificial Language Experiment), the first two Artificial Improvisors, each with a unique composition and embodiment. This work highlights research and development, successes and failures along the way, celebrates collaborations enabling progress, and presents discussions for future work in the space of artificial improvisation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Just a fraction of user studies on professional writers' perception and use of AI systems focused on theatre.
“of which just a fraction focused on theatre [36,38,40].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [36]
The Abstract and Results identify this as a study of AI in live improvisational theatre, so it supports the citation’s theatre focus. The Results describe audience feedback, while the Discussion says a formal evaluation with expert improvisors was planned; our copy does not establish this as a user study of professional writers’ perceptions or use of AI. This paper alone also cannot establish what fraction of such studies focused on theatre. (LLM, conf=0.84)
Experimental — accuracy not yet measuredParticipants were critical of the trial-and-error strategy, which exposed functional limitations of the system, such as lack of narrative coherence and short memory.
“They were critical of this strategy, which exposed functional limitations of the system, such as lack of narrative coherence and short memory [36,40].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [36]
The Discussion says the system cannot yet tell a cohesive story and suggests memory advances could improve callbacks. The Results describe iterative improvements based on audience feedback, but do not say participants were critical of a trial-and-error strategy or that this strategy exposed those limitations. (LLM, conf=0.84)
Experimental — accuracy not yet measuredMany technical limitations hamper the application of LLMs to creative writing, including short memory, lack of semantic coherence, and common-sense and contextual awareness.
“However, many technical limitations hamper the application of LLMs to creative writing.They include short memory [36,40], lack of semantic coherence [28,40], and common-sense and contextual awareness [36,38].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [36]
The Discussion (page unavailable) says the paper's dialogue system was not trained to tell a cohesive story and that memory-network advances might improve callbacks. This supports concerns about coherence and memory in its improvisational system, but does not establish those limitations for LLMs generally. The citing sentence assigns common-sense and contextual awareness to other references, not this paper. (LLM, conf=0.85)
Experimental — accuracy not yet measuredThe machine could not understand story cohesion and lacked semantic comprehension.
“The machine could not understand story cohesion [36] and lacked semantic comprehension [28,40].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [36]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · see citing works
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · see citing works
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,649 · see citing works
(2004) · Cited by 9,718 · see citing works
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · see citing works
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · see citing works
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452 · see citing works
Generating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894 · see citing works
ELIZA — a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1983) · Communications of the ACM · doi:10.1145/357980.357991 · Cited by 2,765 · see citing works
A Critical Review of Recurrent Neural Networks for Sequence LearningPreprint
Lipton, Z. C., Berkowitz, J. A., & Elkan, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.00019 · Cited by 2,711 · see citing works
Computing Machinery and Intelligence
Turing, A. M. (2007) · Springer eBooks · doi:10.1007/978-1-4020-6710-5_3 · Cited by 1,439 · see citing works
Vinyals, O., & Le, Q. (2015) · arXiv · doi:10.48550/arxiv.1506.05869 · Cited by 1,400 · see citing works
Liu, C., Lowe, R., Serban, I. V., Noseworthy, M., Charlin, L., & Pineau, J. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1230 · Cited by 1,262 · see citing works
Deep Reinforcement Learning for Dialogue Generation
Li, J., Monroe, W., Ritter, A., Jurafsky, D., Galley, M., & Gao, J. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1127 · Cited by 1,221 · see citing works
Neural Responding Machine for Short-Text Conversation
Shang, L., Lu, Z., & Li, H. (2015) · doi:10.3115/v1/p15-1152 · Cited by 1,009 · see citing works
Adversarial Learning for Neural Dialogue Generation
Li, J., Monroe, W., Shi, T., Jean, S., Ritter, A., & Jurafsky, D. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1230 · Cited by 880 · see citing works
Liu, C., Lowe, R., Serban, I. V., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08023 · Cited by 603 · see citing works
Context dependent recurrent neural network language model
Mikolov, T., & Zweig, G. (2012) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2012.6424228 · Cited by 570 · see citing works
Deep Reinforcement Learning for Dialogue GenerationPreprint
Li, J., Monroe, W., Ritter, A., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.01541 · Cited by 405 · see citing works
Danescu-Niculescu-Mizil, C., & Lee, L. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1106.3077 · Cited by 329 · see citing works
Neural Responding Machine for Short-Text ConversationPreprint
Shang, L., Lu, Z., & Li, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.02364 · Cited by 212 · see citing works
Impro: Improvisation and the Theatre
Shafer, G., Johnstone, K., & Barker, C. (1980) · Theatre Journal · doi:10.2307/3207427 · Cited by 211 · see citing works
Adversarial Learning for Neural Dialogue GenerationPreprint
Li, J., Monroe, W., Shi, T., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.06547 · Cited by 211 · see citing works
Adversarial Generation of Natural Language
Subramanian, S., Rajeswar, S., Dutil, F., Pal, C., & Courville, A. C. (2017) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w17-2629 · Cited by 171 · see citing works
Towards an open-domain conversational system fully based on natural language processing
Higashinaka, R., Imamura, K., Meguro, T., Miyazaki, C., Kobayashi, N., Sugiyama, H., Hirano, T., Makino, T., & Matsuo, Y. (2014) · International Conference on Computational Linguistics · Cited by 158 · see citing works
Believable Agents and Intelligent Story Adaptation for Interactive Storytelling
Riedl, M., & Stern, A. (2006) · Lecture notes in computer science · doi:10.1007/11944577_1 · Cited by 135 · see citing works
Computational Human-Robot Interaction
Thomaz, A. L., Hoffman, G., & Çakmak, M. (2016) · Foundations and Trends in Robotics · doi:10.1561/2300000049 · Cited by 133 · see citing works
Extrapolating human judgments from skip-gram vector representations of word meaning
Hollis, G., Westbury, C. F., & Lefsrud, L. (2016) · Quarterly Journal of Experimental Psychology · doi:10.1080/17470218.2016.1195417 · Cited by 113 · see citing works
Interactive improvisation with a robotic marimba player
Hoffman, G., & Weinberg, G. (2011) · Autonomous Robots · doi:10.1007/s10514-011-9237-0 · Cited by 100 · see citing works
Adversarial Generation of Natural LanguagePreprint
Rajeswar, S., Subramanian, S., Dutil, F., Pal, C., & Courville, A. C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10929 · Cited by 98 · see citing works
An empirical study of cognition and theatrical improvisation
Magerko, B. S., Manzoul, W., Riedl, M. O., Baumer, A., Fuller, D., Luther, K., & Pearce, C. (2009) · Creativity and Cognition · doi:10.1145/1640233.1640253 · Cited by 83 · see citing works
Improvise.: Scene from the Inside Out
Napier, M. (2004) · Medical Entomology and Zoology · Cited by 40 · see citing works
A Knowledge-Based Framework for the Collaborative Improvisation of Scene Introductions
O’Neill, B., Piplica, A., Fuller, D., & Magerko, B. S. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25289-1_10 · Cited by 35 · see citing works
Improvisational Computational Storytelling in Open Worlds
Martin, L. J., Harrison, B. E., & Riedl, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48279-8_7 · Cited by 33 · see citing works
HERB's Sure Thing: A rapid drama system for rehearsing and performing live robot theater
Zeglin, G. J., Walsman, A., Herlant, L., Zheng, Z., Guo, Y., Koval, M. C., Lenzo, K., Tay, H. J., Velagapudi, P., Correll, K., et al. (2014) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso.2014.7020993 · Cited by 23 · see citing works
Computers and Creativity: The Road Ahead
McCormack, J., & d’Inverno, M. (2012) · Springer eBooks · doi:10.1007/978-3-642-31727-9_16 · Cited by 22 · see citing works
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-controlPreprint
Jaques, N., Gu, S., Bahdanau, D., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02796 · Cited by 22 · see citing works
Interactive Improvisation with a Robotic Marimba Player
Hoffman, G., & Weinberg, G. (2011) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-22291-7_14 · Cited by 21 · see citing works
Mathewson, K. W., & Pilarski, P. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.06979 · Cited by 16 · see citing works
Self-citationEmploying Fuzzy Concept for Digital Improvisational Theatre
Magerko, B., Dohogne, P., & Deleon, C. (2011) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v7i1.12432 · Cited by 15 · see citing works
Experience driven design of creative systems
Yee-King, M. J., & d’Inverno, M. (2016) · Goldsmiths (University of London) · Cited by 11 · see citing works
Designing improvisational interfaces
McCormack, J., & d’Inverno, M. (2016) · Goldsmiths (University of London) · Cited by 9 · see citing works
Feature-rich continuous language models for speech recognition
Mirowski, P., Chopra, S., Balakrishnan, S., et al. (2010) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2010.5700858 · Cited by 5 · see citing works
Self-citationAffect Detection and an Automated Improvisational AI Actor in E-Drama
Zhang, L., Gillies, M. F. P., Barnden, J. A., Hendley, R., Lee, M. G., & Wallington, A. M. (2007) · Springer eBooks · doi:10.1007/978-3-540-72348-6_17 · Cited by 4 · see citing works
Sequence Level Training with Recurrent Neural Networks
Ranzato, M., Chopra, S., Auli, M., & Zaremba, W. (2015) · arXiv · doi:10.48550/arxiv.1511.06732
Flagged first, then by citations
Research works printed but not linked: 11
- [1]1. Arik, S. O., et al. 2017. Deep Voice: Real-time Neural Text- to-Speech. ArXiv e-prints.
- [2]2. Blei, D. M.; Ng, A. Y.; and Jordan, M. I. 2003. Latent dirich- let allocation. JMLR 3(Jan):993-1022.
- [7]7. Glass, J. 1999. Challenges for spoken dialogue systems. In Proc 1999 IEEE ASRU Wkshp.
- [9]9. Hayes-Roth, B., and Van Gent, R. 1996. Improvisational pup- pets, actors, and avatars. In Proc Computer Game Developers Conf.
- [11]11. Hochreiter, S., and Schmidhuber, J. 1997. Long short-term memory. Neural computation 9(8):1735-1780.
- [16]16. Kiros, R.; Zhu, Y.; Salakhutdinov, R. R.; Zemel, R.; Urtasun, R.; Torralba, A.; and Fidler, S. 2015. Skip-thought vectors. In Advances in NIPS, 3294-3302.
- [31]31. Mori, M.; MacDorman, K. F.; and Kageki, N. 2012. The uncanny valley [from the field]. IEEE Robotics & Automation Magazine 19(2):98-100.
- [35]35. Papineni, K.; Roukos, S.; Ward, T.; and Zhu, W.-J. 2002. Bleu: a method for automatic evaluation of machine transla- tion. In Proc 40th Meeting on Association for Computational Linguistics, 311-318.
- [37]37. Perlin, K., and Goldberg, A. 1996. Improv: A system for scripting interactive actors in virtual worlds. In Proc Conf on Computer Graphics and Interactive Techniques, 205-216. ACM.
- [47]47. Martens, J.; and Hinton, G. E. 2011. Generat- ing text with recurrent neural networks. In Proc 28th ICML, 1017-1024.
- [49]49. Thomaz, A.; Hoffman, G.; Cakmak, M.; et al. 2016. Compu- tational human-robot interaction. Foundations and Trends R in Robotics 4(2-3):105-223.
Cited by
Sorted by citations
Mirowski, P., Mathewson, K. W., Pittman, J., & Evans, R. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581225 · Cited by 240 · see citing works
Self-citationImprobotics: Exploring the Imitation Game Using Machine Intelligence in Improvised Theatre
Mathewson, K., & Mirowski, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v14i1.13030 · Cited by 18 · see citing works
Self-citationPlaywriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes
Grigis, P., & De Angeli, A. (2024) · Proceedings of the 2024 International Conference on Advanced Visual Interfaces · doi:10.1145/3656650.3656688 · Cited by 13 · see citing works
Collaborative Storytelling with Human Actors and AI Narrators
Branch, B., Mirowski, P., & Mathewson, K. W. (2021) · arXiv · doi:10.48550/arxiv.2109.14728 · Cited by 11 · see citing works
Self-citation
- Authors
- Mathewson, K., & Mirowski, P.
- Affiliations
- University of Alberta (CA)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Published
- 2017-10-09
- Volume
- 13
- Issue
- 1
- Pages
- 66-72
- ISSN
- 2326-909X (ISSN-L)
- 2334-0924
- OpenAlex
- W2759254424
- Cited by
- 31
- References
- 45
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 6 · 2023: 4 · 2022: 5 · 2021: 4 · 2020: 2 · 2019: 6 · 2018: 1
- FWCI
- 1.12
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Keywords
- improvisational theatre, chatbots, open-domain dialogue, live performance, human-AI collaboration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
