Question answering in the context of stories generated by computers


In this study a model of question answering (called QUEST) is tested in the context of short stories. College students first read a story and then judged the quality of answers to questions about episodes in the story. The model could account for the goodness-of-answer judgments and decision latencies of 5 categories of questions: why, how, when, enablement, and consequence. QUEST specifies the information sources that are activated during question answering; the content of each information source is structured according to a theory of knowledge representation. QUEST specifies the convergence processes that dramatically narrow down the set of possible answers (activated from the information sources) to a small set of good answers to a question.

Advances in Cognitive Systems