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. However, 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. Building on an existing animation generation system for screenwriting, we create a robust NLP pipeline to extract information from screenplays and map them to the systemu0027s knowledge base. We develop a set of linguistic transformation 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 existing 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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/s19-1032 | North American Chapter of the Association for Computational Linguistics |
Field | DocType | Volume |
Text simplification,Computer science,Screenwriting,Natural language,Storyboard,Animation,Natural language processing,Artificial intelligence,Knowledge base,Sentence | Journal | abs/1904.05440 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yeyao Zhang | 1 | 0 | 0.34 |
Eleftheria Tsipidi | 2 | 0 | 0.34 |
Sasha Schriber | 3 | 10 | 2.23 |
Mubbasir Kapadia | 4 | 546 | 58.07 |
Markus H. Gross | 5 | 10154 | 549.95 |
Ashutosh Modi | 6 | 52 | 6.16 |