The dissertation provides an analysis of how the content and organization of explanations function to achieve communicative goals under potentially conflicting constraints, and applies this analysis to the design of a planner for generation of explanations by computer. An implementation of this planner as a multimedia question answering system is described. The functional analysis has four major subparts: (1) A theory of the kinds of knowledge that can provide the basis for "informatively satisfying" responses to a given question. (2) A theory of context sensitive constraints on the choice between alternate domain models that compete as the basis for answering a given question. (3) A theory of how supplemental explanations aid the comprehension and retention of the primary explanation. (4) A theory of how the sequencing of the parts of an explanation enhances the communicative functionality of those parts. The functional aspects of explanation just outlined imply a variety of explanation planning subtasks having distinct information processing requirements. A planning architecture is presented that matches these planning subtasks to appropriate mechanisms: (1) Top-down goal refinement translates queries into specifications of relevant knowledge on which a response can be based. (2) Prioritized preferences restrict competing domain models to those that are expected to be both informative and comprehensible to the questioner at a given point in the dialogue. (3) Plan critics examine the evolving plan and post new goals to supplement the explanation as needed. (4) A constrained graph traversal mechanism sequences the parts of an explanation in a manner respecting certain functional relationships between the parts. Contributions include: (1) the clarification and integration of a variety of functional aspects of explanatory text, (2) an analysis of the roles and limitations of various explanation planning mechanisms, (3) the design of a flexible explanation planner that applies various constraints on explanation independently of each other, and (4) an approach to selection between multiple domain models that is more general than previous approaches. Together these contributions clarify the correspondence between knowledge about communication, planning tasks, and types of discourse structure and provide improved interactive explanation capabilities.
| Identifer | oai:union.ndltd.org:UMASS/oai:scholarworks.umass.edu:dissertations-8681 |
| Date | 01 January 1993 |
| Creators | Suthers, Daniel Derwent |
| Publisher | ScholarWorks@UMass Amherst |
| Source Sets | University of Massachusetts, Amherst |
| Language | English |
| Detected Language | English |
| Type | text |
| Source | Doctoral Dissertations Available from Proquest |
Page generated in 0.0078 seconds