Synthetic Interviews: The Art of Creating a u22Dyadu22 Between Humans and Machine-Based Characters

摘要

Synthetic Interviews is a technology developed at Carnegie Mellon University (CMU) in Pittsburgh, Pennsylvania, by Scott Stevens, Ph.D. and Michael Christel, Ph.D., computer researchers in CMU’s School of Computer Science and Software Engineering Institute. Synthetic Interviews provide a means of conversing in-depth with an individual or character, permitting users to ask questions in a conversational manner (just as they would if they were interviewing the figure face-to-face), and receive relevant, pertinent answers to the questions asked. Existing Synthetic Interviews are accessible via either typed or spoken interfaces. Through this exploration of the CG-persona, users are able to discover a character’s behavior, likes and dislikes, values, qualities, influences, beliefs, or personal knowledge. The Synthetic Interview also strives to capture and convey the core human attributes of reflection, humor, perplexity, bewilderment, frustration, and enjoyment. Synthetic Interviews therefore attempt to create nothing less than a ‘dyad.’ A ‘dyad’ is any two individuals maintaining a socially significant relationship (though this is not to imply that Synthetic Interviews are to remain limited to one-on-one experiences; in fact, Synthetic Interviews utilizing multiple interviewers or interviewees are currently being developed).