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 E FULL PROMPT PREFIXES FOR DRAMATRON E.1 About the Prompt Sets In our study we relied on two sets of prompts: Medea and Sci-Fi. Medea prompts are based on Ancient Greek tragedy Medea, by Euripides (431 BC). The dialogue prompts were taken verbatim from the translation of the play by E. P. Coleridge (1863 - 1936), available in the public domain[13]. We replaced CHORUS by WOMEN OF CORINTH. The plot and character prompts were written from a summary taken from Spark Notes[14] and Wikipedia[15]. To encourage the generation of different locations, Aristotle’s Unity of Place is not respected, and location “Outside the Royal Palace” is renamed as “Medea’s modest home” as well as “On a winged chariot” (even though these are the same locations in the original tragedy). Prompts for Antigone[16] (Sophocles), The Bacchae[17] (Euripides), and The Frogs[18] (Aristophanes) were adapted from Wikipedia and ancient-literature.com The Star Wars log line was adapted from chapter “Creating the killer log line” by Bill Lundy[19]. Sci-Fi character prompts were adapted from Star Wars: Episode IV - A New Hope (1977), written and directed by George Lucas, produced by Lucasfilm and distributed by 20th Century Fox. We also adapted the breakdown of Star Wars into a Hero Journey[20]. The script[21], plot[22] and log line[23] of Plan 9 from Outer Space, which is in public domain. E.2 Title Prompt Prefixes In the following sets of prompt prefixes, the <LOG_LINE> is provided by the writer. E.3 Character Description Prompt Prefixes In the following sets of prompt prefixes, the <LOG_LINE> is provided by the writer. E.4 Plot Outline Prompt Prefixes In the following sets of prompt prefixes, the <LOG_LINE>is provided by the writer and each <CHARACTER_DESCRIPTION> is generated in the previous step. E.5 Location Description Prompt Prefixes In the following sets of prompt prefixes, the <LOG_LINE> is provided by the writer and each <LOCATION_NAME> is generated in the previous step. E.6 Scene Dialogue Prompt Prefixes In the following sets of prompt prefixes, the <LOG_LINE> is provided by the writer, <PLOT_ELEMENT>, <BEAT>, <PREVIOUS_BEAT> and <LOCATION_NAME> are generated during the plot outline generation step, <LOCATION_DESCRIPTION> is generated during the location generation step, <CHARACTER_DESCRIPTION>and each is generated in the character generation step. <PREVIOUS_BEAT> corresponds to <BEAT>from the previous scene (it is left empty for the first scene). Only characters whose name appears in the beat are used in this prompt prefix (we use string matching to select these character names). This paper is available on arxiv under CC 4.0 license. [13] http://classics.mit.edu/Euripides/medea.pl.txt [14] https://www.sparknotes.com/lit/medea/ [15] https://en.wikipedia.org/wiki/Medea_(play) [16] https://www.ancient-literature.com/greece_sophocles_antigone.html [17] https://en.wikipedia.org/wiki/The_Bacchae [18] https://www.ancient-literature.com/greece_aristophanes_frogs.html [19] In Ellis, Sherry, and Laurie Lamson. “Now Write! Mysteries: Suspense, Crime, Thriller, and Other Mystery Fiction Exercises from Today’s Best Writers and Teachers.”, Penguin, 2011 [20] https://thescriptlab.com/features/screenwriting-101/12309-the-heros-journey-breakdown-star-wars/ [21] http://www.horrorlair.com/scripts/criswell.txt [22] https://en.wikipedia.org/wiki/Plan_9_from_Outer_Space [23] https://www.rottentomatoes.com/m/plan-9-from-outer-space 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 E FULL PROMPT PREFIXES FOR DRAMATRON E.1 About the Prompt Sets In our study we relied on two sets of prompts: Medea and Sci-Fi. Medea prompts are based on Ancient Greek tragedy Medea, by Euripides (431 BC). The dialogue prompts were taken verbatim from the translation of the play by E. P. Coleridge (1863 - 1936), available in the public domain[13]. We replaced CHORUS by WOMEN OF CORINTH. The plot and character prompts were written from a summary taken from Spark Notes[14] and Wikipedia[15]. To encourage the generation of different locations, Aristotle’s Unity of Place is not respected, and location “Outside the Royal Palace” is renamed as “Medea’s modest home” as well as “On a winged chariot” (even though these are the same locations in the original tragedy). Prompts for Antigone[16] (Sophocles), The Bacchae[17] (Euripides), and The Frogs[18] (Aristophanes) were adapted from Wikipedia and ancient-literature.com The Star Wars log line was adapted from chapter “Creating the killer log line” by Bill Lundy[19]. Sci-Fi character prompts were adapted from Star Wars: Episode IV - A New Hope (1977), written and directed by George Lucas, produced by Lucasfilm and distributed by 20th Century Fox. We also adapted the breakdown of Star Wars into a Hero Journey[20]. The script[21], plot[22] and log line[23] of Plan 9 from Outer Space, which is in public domain. E.2 Title Prompt Prefixes In the following sets of prompt prefixes, the < LOG_LINE > is provided by the writer. LOG_LINE E.3 Character Description Prompt Prefixes In the following sets of prompt prefixes, the < LOG_LINE > is provided by the writer. LOG_LINE E.4 Plot Outline Prompt Prefixes In the following sets of prompt prefixes, the < LOG_LINE >is provided by the writer and each < CHARACTER_DESCRIPTION > is generated in the previous step. LOG_LINE CHARACTER_DESCRIPTION E.5 Location Description Prompt Prefixes In the following sets of prompt prefixes, the <LOG_LINE> is provided by the writer and each < LOCATION_NAME > is generated in the previous step. LOCATION_NAME E.6 Scene Dialogue Prompt Prefixes In the following sets of prompt prefixes, the < LOG_LINE > is provided by the writer, < PLOT_ELEMENT >, < BEAT >, < PREVIOUS_BEAT > and < LOCATION_NAME > are generated during the plot outline generation step, < LOCATION_DESCRIPTION > is generated during the location generation step, < CHARACTER_DESCRIPTION >and each is generated in the character generation step. < PREVIOUS_BEAT > corresponds to < BEAT >from the previous scene (it is left empty for the first scene). Only characters whose name appears in the beat are used in this prompt prefix (we use string matching to select these character names). LOG_LINE PLOT_ELEMENT BEAT PREVIOUS_BEAT LOCATION_NAME LOCATION_DESCRIPTION CHARACTER_DESCRIPTION PREVIOUS_BEAT BEAT 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 [13] http://classics.mit.edu/Euripides/medea.pl.txt [14] https://www.sparknotes.com/lit/medea/ [15] https://en.wikipedia.org/wiki/Medea_(play) [16] https://www.ancient-literature.com/greece_sophocles_antigone.html [17] https://en.wikipedia.org/wiki/The_Bacchae [18] https://www.ancient-literature.com/greece_aristophanes_frogs.html [19] In Ellis, Sherry, and Laurie Lamson. “Now Write! Mysteries: Suspense, Crime, Thriller, and Other Mystery Fiction Exercises from Today’s Best Writers and Teachers.”, Penguin, 2011 [20] https://thescriptlab.com/features/screenwriting-101/12309-the-heros-journey-breakdown-star-wars/ [21] http://www.horrorlair.com/scripts/criswell.txt [22] https://en.wikipedia.org/wiki/Plan_9_from_Outer_Space [23] https://www.rottentomatoes.com/m/plan-9-from-outer-space

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

The Day the Pool Pit Burned Down - An AI-Generated Script from Dramatron 

Quantitative Evaluation of AI Writing Tools: Insights from Likert Scale Responses

Teleplay.Tech

Too Long; Didn't Read

Make resilience your competitive advantage

Diverse AI Prompt Prefixes for Scriptwriting: From Star Wars to Ancient Drama

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

Advancing Multimodal Video Generation with Responsible AI and Stylization

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

Advancing Multimodal Video Generation with Responsible AI and Stylization

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

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps