Processing open text input in a scripted communication scenario: Extended abstract

Serious games often employ pre-scripted dialogues and interactions with a player; in contrast to free user input that enables deeper immersion. In this paper we explore possibilities for interactive natural language dialogue in a serious game by combining Natural Language Processing (NLP) techniques with dialogue management. Our game learning environment has a communication scenario editor in which a domain expert develops a structured, scripted scenario as a sequence of potential interactions. A communication scenario is context-specific and often follows a protocol - for instance, delivering bad news to a patient. Currently, a player navigates through a simulation and converses with a virtual character by choosing a statement option from one of the prescripted player statements, at each step in the simulation. We develop a scenario-specific corpus method (SSCM) to process open responses (i.e. natural language inputs) in our learning environment. We conduct an experiment to collect data for comparing SSCM against multiple NLP methods, and another experiment to investigate if framing can improve processing open-text input using SSCM in a communication simulation.