Generating Animations from Screenplays

 

In this paper, we develop a text-to-animation system which is capable of handling complex sentences.

June 1, 2019
*SEM 2019

 

Authors

Yeyao Zhang (Disney Research/ETH Joint M.Sc.)

Eleftheria Tsipidi (Disney Research)

Sasha Schriber (Disney Research)

Mubbasir Kapadia (Disney Research/Rutgers University)

Markus Gross (Disney Research/ETH Zurich)

Ashutosh Modi (Disney Research)

Generating Animations from Screenplays

Abstract

Automatically generating animation from natural language text finds application in a number of areas e.g. movie script writing, instructional videos, and public safety. How- ever, translating natural language text into animation is a challenging task. Existing text-to-animation systems can handle only very simple sentences, which limits their applications. In this paper, we develop a text-to-animation system which is capable of handling complex sentences. We achieve this by introducing a text simplification step into the process. Build- ing on an existing animation generation system for screenwriting, we create a robust NLP pipeline to extract information from screen- plays and map them to the system’s knowledge base. We develop a set of linguistic trans- formation rules that simplify complex sentences. Information extracted from the simplified sentences is used to generate a rough storyboard and video depicting the text. Our sentence simplification module outperforms exist- ing systems in terms of BLEU and SARI metrics.We further evaluated our system via a user study: 68% participants believe that our system generates reasonable animation from input screenplays.

Copyright Notice