A lightweight story-comprehension approach to game dialogue

Robert van Leeuwen, Yun-Gyung Cheong, Mark J. Nelson (2012). A lightweight story-comprehension approach to game dialogue. In Proceedings of the Workshop on Games and NLP.


In this paper we describe Answery, a rule-based system that allows authors to specify game characters' background stories in natural language. The system parses these background stories, applies transformation rules to turn them into semantic content, and generates dialogue during gameplay by posing it as a question-answering problem. By the means of simple categorization combined with rule inference engine our system can generate answers efficiently. Our initial pilot study shows that this approach is promising.

Back to publications.