Question answering in the context of stories.

Abstract

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.

Towards intelligent authoring tools for machinima creation

“…To be useful, the system must be able to provide feedback on that incomplete artifact. Our investigation of computer-asaudience currently focuses on the development of computational equivalents to (a) cognitive models of narrative [3], (b) cognitive inferencing by readers of narratives [4], and (c) the discursive linkages between visual medium and narrative [1]. Reasoning about narrative from the perspective of the intended audience is hard; we believe that this capability for feedback from the viewer perspective will further strengthen the creative abilities of novice machinima authors.…”

Question-Driven Explanatory Reasoning About Devices that Malfunction

“…The composition of these conceptual graph structures is not arbitrary, but is based on formal and conceptual constraints that have been studied for three decades. For example, the categories of nodes and arcs are functionally adequate for implementing models of question answering and questions asking that have been supported in experiments on adults (Graesser & Hemphill, 1991;Graesser, Lang, & Roberts, 1991;Otero & Graesser, in press). At the center, there is a causal chain of events that unfold when the key successfully unlocks the door.…”

A Software Agent Model of Consciousness

“…Later, CMattie may be again conscious of the completely understood message without having been conscious of the process of retrieving the seminar name. Research on human question answering has revealed that the search of information is unconscious, fast, and executed in parallel, whereas the process of verifying that a fetched answer is correct is conscious, slow, and serial (Graesser, Lang, and Roberts 1991).…”