Title :
From socio-emotional scenarios to expressive virtual narrators
Author :
Miletitch, Roman ; Sabouret, Nicolas ; Ochs, Magalie
Author_Institution :
Lab. d´´Inf. de Paris 6 (LIP6), Univ. Pierre et Marie Curie, Paris, France
Abstract :
Telling a story requires linking a series of significant events using statements to maintain tension, create suspense and allow time for the development of emotions. When automating this process, one major challenge is the generation of these filling sentences and ensuring that they are sufficiently consistent with the story. To this end we propose in this paper to use a knowledge representation model of a local coherent world. We present a scheme for automatic storytelling based on an ontological representation of concepts and natural language generation algorithms that dynamically build relations between concepts. Our algorithms scan the scenario to build a sentence skeleton that will be enriched using pseudo-random queries in the ontology. This allows us to enrich the story while keeping the storyline coherent. We end by discussing our evaluation and presenting our preliminary results.
Keywords :
emotion recognition; human computer interaction; humanities; multi-agent systems; natural languages; ontologies (artificial intelligence); social aspects of automation; virtual reality; automatic storytelling; concept ontological representation; expressive virtual narrators; knowledge representation model; multiagent framework; natural language generation algorithms; pseudo-random queries; sentence skeleton; socio-emotional scenarios; virtual story teller; Games; Heuristic algorithms; Libraries; Natural languages; Ontologies; Semantics; Vocabulary;
Conference_Titel :
Affective Computational Intelligence (WACI), 2011 IEEE Workshop on
Conference_Location :
Paris
Print_ISBN :
978-1-61284-083-3
DOI :
10.1109/WACI.2011.5953151