Face marks figures of faces which consist of characters such as (""), and are effective for expressin emotions.in a textdialogue s stem We usually fietermine face marks from {isto+ of emotional elements and actional elements. This aper natural language dialogue s stem from chat dialogue data in the Intemet. etc. d use a back uroDapabon proposes a method of learning face marks F or a error kamin of a thrcc-layer ncural nctwbrk'toleam a modcl of s acc marks. In this ncural network, the input neurons express emotional parameters and actional categories of texts, and the output neurons express parts of face marks: mouth, e es, arms, and optional things. The experimental resuk showed that the learning error \vas 0.19, and we could get the erformance approxlmately 93 % permiss,ible valueFor the leamin set of dialo ues and ap roxlmately 60 that our system acquired the ood information of relationship between arts of face marks and emotional and actional efements.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.