M2D: Monolog to Dialog Generation for Conversational Story Telling

摘要: Storytelling serves many different social functions, e.g. stories are used to persuade, share troubles, establish shared values, learn behaviors, and entertain. Moreover, often told conversationally through dialog, previous work suggests that information provided dialogically is more engaging than when in monolog. In this paper, we present algorithms for converting a deep representation of story into dialogic storytelling, can vary aspects the telling, including personality storytellers. We conduct several experiments test whether storytellings engaging, automatically generated variants linguistic form correspond differences be recognized an extended storytelling dialog.