Using Synthetically Collected Scripts for Story Generation

Takashi Ogata, Tatsuya Arai, Jumpei Ono


Abstract
A script is a type of knowledge representation in artificial intelligence (AI). This paper presents two methods for synthetically using collected scripts for story generation. The first method recursively generates long sequences of events and the second creates script networks. Although related studies generally use one or more scripts for story generation, this research synthetically uses many scripts to flexibly generate a diverse narrative.
Anthology ID:
C16-2053
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations
Month:
December
Year:
2016
Address:
Osaka, Japan
Editor:
Hideo Watanabe
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
253–257
Language:
URL:
https://aclanthology.org/C16-2053
DOI:
Bibkey:
Cite (ACL):
Takashi Ogata, Tatsuya Arai, and Jumpei Ono. 2016. Using Synthetically Collected Scripts for Story Generation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations, pages 253–257, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Using Synthetically Collected Scripts for Story Generation (Ogata et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/C16-2053.pdf