Shaping the Narrative Arc: An Information-Theoretic Approach to
Collaborative Dialogue
release_77e7abhma5fufjdcc7tjoatth4
by
Kory W. Mathewson, Pablo Samuel Castro, Colin Cherry, George Foster,
Marc G. Bellemare
2019
Abstract
We consider the problem of designing an artificial agent capable of
interacting with humans in collaborative dialogue to produce creative, engaging
narratives. In this task, the goal is to establish universe details, and to
collaborate on an interesting story in that universe, through a series of
natural dialogue exchanges. Our model can augment any probabilistic
conversational agent by allowing it to reason about universe information
established and what potential next utterances might reveal. Ideally, with each
utterance, agents would reveal just enough information to add specificity and
reduce ambiguity without limiting the conversation. We empirically show that
our model allows control over the rate at which the agent reveals information
and that doing so significantly improves accuracy in predicting the next line
of dialogues from movies. We close with a case-study with four professional
theatre performers, who preferred interactions with our model-augmented agent
over an unaugmented agent.
In text/plain
format
Archived Files and Locations
application/pdf 2.5 MB
file_ivotsoroezer5pyevio5pkoivm
|
arxiv.org (repository) web.archive.org (webarchive) |
1901.11528v1
access all versions, variants, and formats of this works (eg, pre-prints)