Combinatorial Dialogue Authoring

We present an annotation scheme and combinatorial authoring procedure by which a small base of annotated human-authored dialogue exchanges can be exploited to automatically generate many new exchanges. The combinatorial procedure builds recombinant exchanges by reasoning about individual lines of dialogue in terms of their mark-up, which is attributed during annotation and captures what a line expresses about the story world and what it specifies about lines that may precede or succeed it in new contexts. From a human evaluation task, we find that while our computer-authored recombinant dialogue exchanges are not rated as highly as human-authored ones, they still rate quite well and show more than double the strength of the latter in expressing game state. We envision immediate practical use of our method in a collaborative authoring scheme in which, given a small database of annotated dialogue, the computer instantly generates many full exchanges that the human author then polishes, if necessary. We believe that combinatorial dialogue authoring represents an immediate and huge reduction in authorial burden relative to current authoring practice.