Authors:
(1) PIOTR MIROWSKI and KORY W. MATHEWSON, DeepMind, United Kingdom and Both authors contributed equally to this research;
(2) JAYLEN PITTMAN, Stanford University, USA and Work done while at DeepMind;
(3) RICHARD EVANS, DeepMind, United Kingdom. Table of Links Abstract and Intro Storytelling, The Shape of Stories, and Log Lines The Use of Large Language Models for Creative Text Generation Evaluating Text Generated by Large Language Models Participant Interviews Participant Surveys Discussion and Future Work Conclusions, Acknowledgements, and References A. RELATED WORK ON AUTOMATED STORY GENERATION AND CONTROLLABLE STORY GENERATION B. ADDITIONAL DISCUSSION FROM PLAYS BY BOTS CREATIVE TEAM C. DETAILS OF QUANTITATIVE OBSERVATIONS D. SUPPLEMENTARY FIGURES E. FULL PROMPT PREFIXES FOR DRAMATRON F. RAW OUTPUT GENERATED BY DRAMATRON G. CO-WRITTEN SCRIPTS B ADDITIONAL DISCUSSION FROM PLAYS BY BOTS CREATIVE TEAM Discussions amongst the creative team were summarized in the body of the text (see Section 5.9). To reiterate, four key themes emerged through these discussions which echo the themes presented in Section 5. These themes are discussed in detail in this section, alongside supporting quotes. First, the system has a distinct glitch style that can sometimes be nonsensical, vague, or passive. As one performer recounted, “sometimes there is internal conflict within the text, and in those moments it is as if [Dramatron] is working against itself”. This pushes performers to commit to choices, and to be concise and specific and complimentary in their interpretation. One performer noted that if the system generated flawless text, “it might not work as well”, because “the mistakes in the script are the joy”. Another went a step further, saying “I almost want more curveballs and non-sequiturs... more crunchy bits”. Overall, the sentiment of enjoying the style of the system was a common theme, with several of the performers remarking that “some of the funniest parts are when you can tell a robot made it”, and that the audience “wants to hear the robot’s voice”. Secondly, the generated text can sometimes be repetitive. This can be interpreted as a mistake. Or, this repetition can be fun and playful if it is interpreted as an important and deliberate choice from the playwright: “a choice to be honored,” as one performer said. When the system did repeat itself, the cast was able to make the lines more meaningful with their own unique human talents. As one said, “you can do so much with your line reading, with your physicality, delivery, proximity, and acting choices.” Third, the team discussed agency and expectations of the systems capabilities. For instance, in the way that the performers would refer to the system’s choices. One said “Dramatron was trying to show me the angle,” or “I was trying to understand what Dramatron meant”. Discussions amongst the creative team explored their expectations of what the system could and could not do. For example, “it is just a bot, not really fully understanding how [the world] works”, and another responded “Dramatron is trying.” Finally, the prevailing feedback from the majority of performers was that participating in the production was fun. As one actor said, “it was liberating and easy because the world creating was done for you, the platform was done, and that can be mentally exhausting as an improviser.” These reflections discussed by the creative team reflect the usefulness of co-written scripts. This is particularly true when used for a production such as Plays By Bots, which leverages professional improvisers to interpret the scripts. The co-creativity of a system such as Dramatron extends beyond the playwright and Dramatron, and to the performer on the stage working with the generated and edited text. These reflections discussed by the creative team reflect the usefulness of co-written scripts. This paper is available on arxiv under CC 4.0 license. Authors: (1) PIOTR MIROWSKI and KORY W. MATHEWSON, DeepMind, United Kingdom and Both authors contributed equally to this research; (2) JAYLEN PITTMAN, Stanford University, USA and Work done while at DeepMind; (3) RICHARD EVANS, DeepMind, United Kingdom. Authors: Authors: (1) PIOTR MIROWSKI and KORY W. MATHEWSON, DeepMind, United Kingdom and Both authors contributed equally to this research; (2) JAYLEN PITTMAN, Stanford University, USA and Work done while at DeepMind; (3) RICHARD EVANS, DeepMind, United Kingdom. Table of Links Abstract and Intro Abstract and Intro Storytelling, The Shape of Stories, and Log Lines Storytelling, The Shape of Stories, and Log Lines The Use of Large Language Models for Creative Text Generation The Use of Large Language Models for Creative Text Generation Evaluating Text Generated by Large Language Models Evaluating Text Generated by Large Language Models Participant Interviews Participant Interviews Participant Surveys Participant Surveys Discussion and Future Work Discussion and Future Work Conclusions, Acknowledgements, and References Conclusions, Acknowledgements, and References A. RELATED WORK ON AUTOMATED STORY GENERATION AND CONTROLLABLE STORY GENERATION A. RELATED WORK ON AUTOMATED STORY GENERATION AND CONTROLLABLE STORY GENERATION B. ADDITIONAL DISCUSSION FROM PLAYS BY BOTS CREATIVE TEAM B. ADDITIONAL DISCUSSION FROM PLAYS BY BOTS CREATIVE TEAM C. DETAILS OF QUANTITATIVE OBSERVATIONS C. DETAILS OF QUANTITATIVE OBSERVATIONS D. SUPPLEMENTARY FIGURES D. SUPPLEMENTARY FIGURES E. FULL PROMPT PREFIXES FOR DRAMATRON E. FULL PROMPT PREFIXES FOR DRAMATRON F. RAW OUTPUT GENERATED BY DRAMATRON F. RAW OUTPUT GENERATED BY DRAMATRON G. CO-WRITTEN SCRIPTS G. CO-WRITTEN SCRIPTS B ADDITIONAL DISCUSSION FROM PLAYS BY BOTS CREATIVE TEAM Discussions amongst the creative team were summarized in the body of the text (see Section 5.9). To reiterate, four key themes emerged through these discussions which echo the themes presented in Section 5. These themes are discussed in detail in this section, alongside supporting quotes. First, the system has a distinct glitch style that can sometimes be nonsensical, vague, or passive. As one performer recounted, “sometimes there is internal conflict within the text, and in those moments it is as if [Dramatron] is working against itself”. This pushes performers to commit to choices, and to be concise and specific and complimentary in their interpretation. One performer noted that if the system generated flawless text, “it might not work as well”, because “the mistakes in the script are the joy”. Another went a step further, saying “I almost want more curveballs and non-sequiturs... more crunchy bits”. Overall, the sentiment of enjoying the style of the system was a common theme, with several of the performers remarking that “some of the funniest parts are when you can tell a robot made it”, and that the audience “wants to hear the robot’s voice”. Secondly, the generated text can sometimes be repetitive. This can be interpreted as a mistake. Or, this repetition can be fun and playful if it is interpreted as an important and deliberate choice from the playwright: “a choice to be honored,” as one performer said. When the system did repeat itself, the cast was able to make the lines more meaningful with their own unique human talents. As one said, “you can do so much with your line reading, with your physicality, delivery, proximity, and acting choices.” Third, the team discussed agency and expectations of the systems capabilities. For instance, in the way that the performers would refer to the system’s choices. One said “Dramatron was trying to show me the angle,” or “I was trying to understand what Dramatron meant”. Discussions amongst the creative team explored their expectations of what the system could and could not do. For example, “it is just a bot, not really fully understanding how [the world] works”, and another responded “Dramatron is trying.” Finally, the prevailing feedback from the majority of performers was that participating in the production was fun. As one actor said, “it was liberating and easy because the world creating was done for you, the platform was done, and that can be mentally exhausting as an improviser.” These reflections discussed by the creative team reflect the usefulness of co-written scripts. This is particularly true when used for a production such as Plays By Bots, which leverages professional improvisers to interpret the scripts. The co-creativity of a system such as Dramatron extends beyond the playwright and Dramatron, and to the performer on the stage working with the generated and edited text. These reflections discussed by the creative team reflect the usefulness of co-written scripts. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

How Exactly Does Dramatron Cook Stories Up

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Advancing Coherent Story Generation: Future Directions for AI Writing Tools

Co-Writing Screenplays and Theatre Scripts with Language Models: Notes from Industrial Professionals

Storytelling, The Shape of Stories, and Log Lines

Understanding Statistical Language Models and Hierarchical Language Generation

Evaluating LLM-Generated Text: Methods, Limitations, and Human-Centric Approaches

Professional Screenwriters Share Pros and Cons of Co-Writing with AI

Advancing Coherent Story Generation: Future Directions for AI Writing Tools

Co-Writing Screenplays and Theatre Scripts with Language Models: Notes from Industrial Professionals

Storytelling, The Shape of Stories, and Log Lines

Understanding Statistical Language Models and Hierarchical Language Generation

Evaluating LLM-Generated Text: Methods, Limitations, and Human-Centric Approaches

Professional Screenwriters Share Pros and Cons of Co-Writing with AI

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps