When a Robot Writes a Play: Automatically Generating a Theatre Play Script

Rosa, Rudolf; Musil, Tomáš; Dušek, Ondřej; Jurko, Dominik; Schmidtová, Patrícia; Mareċek, David; Bojar, Ondřej; Kocmi, Tom; Hrbek, Daniel; Košťák, David; Kinská, Martina; Novàkovâ, Marie; Doležal, Josef; Vosecká, Klára; Studeník, Tomáš; Žabka, Petr

doi:10.1162/isal_a_00372

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many different approaches have been considered and developed in this area, such as a growing forest of stories that automatically clusters documents from different breaking news into events and connecting them to form a cohesive story [11] or THEaiTRE 5 , which emerged with the original idea of having a robot create a theatre play. It premiered on 26 February 2021 with the title "AI: When a Robot Writes a Play" and was watched online by 18 450 devices [12].…”

Section: Text2storyline: Generating Enriched Storylines From Textmentioning

confidence: 99%

See 1 more Smart Citation

Text2Storyline: Generating Enriched Storylines from Text

Gonçalves

Campos

Jorge

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

First of all, I would like to thank Professor Ricardo Campos for all the hours of guidance and patience and for motivating to push through any adversity that arose throughout this project. To Professor Alípio Jorge for providing his expertise on more sensible matters and for his aid in moments of need. I would also like to thank Jorge Duque, who was responsible for developing the Time-Matters online demo, for his availability and help, which were fundamental during the initial stages of this work. Thank you to everyone who took the time to participate in either or both of our surveys.To my family, my biggest thanks to my parents in particular, for the unconditional love and support and for always providing me with everything I could ever need. I could not have gotten this far without them.To all my friends, for showing interest in my work and helping me accomplish this task, but above all for being what a friend should be throughout the years.A special thank you to my girlfriend Yasmin, for always supporting me, especially in the toughest moments and for listening to my endless ramblings about this project.

show abstract

Section: Text2storyline: Generating Enriched Storylines From Textmentioning

confidence: 99%

“…In detail, Heideltime 10 is a multilingual, domain-sensitive temporal tagger developed at the Database Systems Research Group 11 at Heidelberg University 12 . It extracts temporal expressions from documents and normalizes them according to the TIMEX3 annotation standard.…”

Section: Time-mattersmentioning

confidence: 99%

Text2Storyline: Generating Enriched Storylines from Text

Gonçalves

Campos

Jorge

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The project team is composed of experts from three institutions, all based in Prague, Czechia: The THEaiTRobot system (Rosa et al, 2021), which was used to generate the theatre play script, is based on the pre-trained GPT-2 generative language model, created and made available by the OpenAI consortium . A generative language model is a tool that first needs to be trained on large texts; GPT-2 is an artificial neural network trained on 8 million English documents from the internet, thus learning how words can be combined together to form sentences and textual documents.…”

Section: Augmented Lectures As a Research Processmentioning

confidence: 99%

Theatre About Science. Theory and Practice

Montenegro,

Oliveira,

Cruz

et al. 2023

View full text Add to dashboard Cite

This volume reflects the great diversity and different perspectives related to the connections between theatre and the sciences, both regarding the performative practice and the academic thought upon that practice. It also gathers contributions from Literary Studies, Theatre and Performance Studies and Science Communication. It reveals a diverse group of practices, varied stages, different formats, different sized productions and diverse target audiences, that suggest a common quality or characteristic in these intersections that can be activated in varied contexts and with different levels of production. The diversity of voices and experiences present in this volume also carries with it a strong geographical perspective, with reports of practices in different regions of the globe, sketching a wider panorama of theatre and sciences intersections.

show abstract

Barriers to Industry Adoption of AI Video Generation Tools: A Study Based on the Perspectives of Video Production Professionals in China

Yu,

Yang,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In recent years, the rapid advancement of artificial intelligence (AI) in the video sector has captured widespread attention. Despite the proliferation of AI video generation tools targeted at general consumers, there remains a gap in addressing the specialized requirements and advanced functionalities sought by industry professionals. This study aims to identify and overcome the barriers hindering the adoption of AI video tools in the Chinese video industry, thereby facilitating their seamless integration. The research unfolded in two phases employing a comprehensive methodology. Initially, we delineated the industry’s video usage standards, drawing upon both established norms and insights gleaned from seasoned industry experts through focus group interviews. These insights informed the formulation of semi-structured interview questions. Subsequently, in-depth semi-structured interviews were conducted with ten Chinese industry experts, leading to the identification of eight primary adoption barriers: innovation, market demand, technological maturity, cross-disciplinary collaboration, ethics and privacy, public acceptance, data security and copyright, and global perspectives and localization. In the second phase, a detailed questionnaire survey involving 401 Chinese industry practitioners validated these factors. A data analysis underscored the significant impact of these eight factors on industry adoption, particularly emphasizing technological maturity. Furthermore, exhaustive examinations and discussions were undertaken for each identified barrier. The findings of this study theoretically bridge the gaps in understanding the impediments to the application of AI video generation tools in the video industry. They offer valuable insights into the current application landscape and furnish pertinent suggestions for advancing technology promotion and development in the future. Ultimately, this research aspires to augment the integration and utilization of AI technology within the Chinese video production industry, thereby propelling its progress and development forward.

show abstract

When a Robot Writes a Play: Automatically Generating a Theatre Play Script

Cited by 3 publications

References 11 publications

Text2Storyline: Generating Enriched Storylines from Text

Text2Storyline: Generating Enriched Storylines from Text

Theatre About Science. Theory and Practice

Barriers to Industry Adoption of AI Video Generation Tools: A Study Based on the Perspectives of Video Production Professionals in China

Contact Info

Product

Resources

About