2020
DOI: 10.48550/arxiv.2006.14668
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

THEaiTRE: Artificial Intelligence to Write a Theatre Play

Abstract: We present THEaiTRE, a starting research project aimed at automatic generation of theatre play scripts. This paper reviews related work and drafts an approach we intend to follow. We plan to adopt generative neural language models and hierarchical generation approaches, supported by summarization and machine translation methods, and complemented with a human-in-the-loop approach.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 7 publications
0
2
0
Order By: Relevance
“…More recently, Rosa et al [2020] proposed THEaiTRE, a mixed framework that consists of generative language models and hierarchical generation approaches that use text summarization and machine translation methods. THEaiTRE finetunes a pre-trained GPT-2 model on a small dataset of formatted theater and movie scripts in English and Czech.…”
Section: Play Script Generationmentioning
confidence: 99%
“…More recently, Rosa et al [2020] proposed THEaiTRE, a mixed framework that consists of generative language models and hierarchical generation approaches that use text summarization and machine translation methods. THEaiTRE finetunes a pre-trained GPT-2 model on a small dataset of formatted theater and movie scripts in English and Czech.…”
Section: Play Script Generationmentioning
confidence: 99%
“…Some believe that AI has made its mark in the field of theatre creation and is even demonstrating some degree of autonomy, despite being in an initial stage of artistic achievement. Nevertheless, with the continuous technological iterations and further expansion of depth, it is reasonable to anticipate potential groundbreaking progression of this technology in artistic creation (Rosa et al, 2006) [3].…”
Section: Introductionmentioning
confidence: 99%