M2D: Monolog to Dialog Generation for Conversational Story Telling

TL;DR

This paper introduces algorithms for transforming monologic stories into engaging dialogic storytelling, allowing variation in storytelling style and personality, and evaluates their effectiveness through experiments.

Contribution

It presents novel algorithms for converting story representations into dialogic forms with personality variations, enhancing storytelling engagement.

Findings

Dialogic storytelling is more engaging than monologue.

Generated personality variants can be recognized in storytelling dialogs.

Algorithms effectively produce diverse, personality-aware storytelling dialogues.

Abstract

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