of Natural Language Film Scripts

Abstract. Producing plays, films or animations is a complex and ex-pensive process involving various professionals and media. Our proposed software system, SceneMaker, aims to facilitate this creative process by automatically interpreting natural language film scripts and generating multimodal, animated scenes from them. During the generation of the story content, SceneMaker gives particular attention to emotional as-pects and their reflection in fluency and manner of actions, body pos-ture, facial expressions, speech, scene composition, timing, lighting, mu-sic and camera work. Related literature and software on Natural Lan-guage Processing, in particular textual affect sensing, affective embodied agents, visualisation of 3D scenes and digital cinematography are re-viewed. In relation to other work, SceneMaker follows a genre-specific text-to-animation methodology which combines all relevant expressive modalities and is made accessible via web-based and mobile platforms. In conclusion, SceneMaker will enhance the communication of creative ideas providing quick pre-visualisations of scenes