View Item 
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UU Student Theses RepositoryBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

        A deep learning architecture for emotional aware chatbots

        Thumbnail
        View/Open
        scriptie.pdf (2.047Mb)
        Publication date
        2020
        Author
        Grouls, R.H.
        Metadata
        Show full item record
        Summary
        Chatbots cover a broad range of possible applications. Interacting with human emotions is a small but necessary subset of the skillset necessary for meaningful interaction. This paper explores strategies to create a chatbot that is able to adapt to the emotional cues during a conversation. A first challenge is to handle the dimensionality of human communication that is addressed with strategies to reduce the dimensionality of both input and output. Additional challenges are handling the continuous action space of semantic vectors and the variations in personality types. I propose an ensemble model of machine learning techniques and conclude with a perspective on the generation of meaning and the consequences this has for a possible implementation
        URI
        https://studenttheses.uu.nl/handle/20.500.12932/37426
        Collections
        • Theses
        Utrecht university logo