Automatic generation of narrative content for digital games

Abstract

Abstract:Interactive simulation games used for training usually require a large amount of coherent narrative content. An effective and efficient solution to the narrative content creation problem is to use Natural Language Generation (NLG) systems. The use of NLG systems, however, requires sophisticated linguistic and sometimes programming knowledge. For this reason, NLG systems are typically not accessible to the game designers who write narrative content. We have designed and implemented a visual environment for creating and modifying NLG templates that requires no programming knowledge, and can operate with a minimum of linguistic knowledge. It allows specifying templates with any number of variables and dependencies between them. It automatically generates all the sentences that follow the created template. It uses SimpleNLG to provide the linguistic background knowledge. We tested the performance of our system in the context of an interactive simulation game.

A Pattern-Based Model for Generating Text to Express Emotion

“…Some are general purpose engines such as FUF [3] and Penman [8], which can be programmed with various linguistic rules. We used SimpleNLG [4] and our Authoring Tool NLG System [1] for sentence realization, and to generate sentence. Using the pattern definitions from the previous sections, we designed a simple surface realization component for our model.…”