Generating Sentence Planning Variations for Story Telling

TL;DR

This paper introduces a new parameterized sentence planner for story generation that enhances variation and discourse manipulation, evaluated through user studies on personal narratives.

Contribution

It develops a domain-independent sentence planning method that enables dynamic variation in storytelling, extending previous work on the ES-Translator to new narrative domains.

Findings

The sentence planner produces diverse story retellings.

User evaluations favor varied narrative styles.

The approach is effective across different storytelling domains.

Abstract

There has been a recent explosion in applications for dialogue interaction ranging from direction-giving and tourist information to interactive story systems. Yet the natural language generation (NLG) component for many of these systems remains largely handcrafted. This limitation greatly restricts the range of applications; it also means that it is impossible to take advantage of recent work in expressive and statistical language generation that can dynamically and automatically produce a large number of variations of given content. We propose that a solution to this problem lies in new methods for developing language generation resources. We describe the ES-Translator, a computational language generator that has previously been applied only to fables, and quantitatively evaluate the domain independence of the EST by applying it to personal narratives from weblogs. We then take advantage of recent work on language generation to create a parameterized sentence planner for story generation that provides aggregation operations, variations in discourse and in point of view. Finally, we present a user evaluation of different personal narrative retellings.