Authors:
(1) Prerak Gandhi, Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai, prerakgandhi@cse.iitb.ac.in, and these authors contributed equally to this work;
(2) Vishal Pramanik, Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai, vishalpramanik,pb@cse.iitb.ac.in, and these authors contributed equally to this work;
(3) Pushpak Bhattacharyya, Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai.
Table of Links
- Abstract and Intro
- Motivation
- Related Work
- Dataset
- Experiments and Evaluation
- Results and Analysis
- Conclusion and Future Work
- Limitations and References
- A. Appendix
2. Motivation
Movies are a form of visual media and can have a huge influence on life and society. Movie scripts are often 30,000 words long, comparable to a 100- page book. Though scripts can be diverse, they have fixed and oft-repeated structures, e.g., scene heading, transition, character name, etc.. This fixity and repetition can be dull and time-consuming and can be handed over to AI. However, a surprising fact is that AI-based models can be creative in generating novel characters and stories. These reasons have motivated the film industry to seriously consider harnessing AI for various aspects of movie making, script and scene writing being one of them.
Los Angeles Times, 19 December 2022, asks, "AI is here, and it’s making movies. Is Hollywood ready?". The newspaper edition reports mainly movie editing efforts ongoing at various places using AI. Our task in the paper is allied but different in the sense that we aim to provide a "script-writers’ assistant"
This paper is available on arxiv under CC 4.0 DEED license.