Abstract

The automatic creation of 3D animation from natural language text is used in many fields. The main target of this paper is to produce a 3D cartoon from a text input. Therefore, we need to analyze the input corpus to extract useful information by employing theories and tools from linguistics and natural language processing in addition to computer graphics for human language visualization. The system operates through two phases. The NLP phase, in which input text passes first through a coreference resolution solver in order to remove pronouns and substitute them with their corresponding nouns followed by a dependency parser in order to detect subject-action-object (SAO) relations in the resolved text. The sequence of SAOs resulting from the NLP phase is passed to the graphics phase. In the graphics phase a 3D animated video cartoon is generated by visualizing each SAO extracted in the NLP phase and Storytelling using the Unity game engine platform. The main contribution of this work is that the input does not have to be a screenplay. It is also demonstrated that performing coreference resolution before dependency parsing resulted in a more compact sequence of SAOs.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.