Causal Reconstruction
dc.date.accessioned | 2004-10-04T14:16:02Z | |
dc.date.accessioned | 2018-11-24T10:11:16Z | |
dc.date.available | 2004-10-04T14:16:02Z | |
dc.date.available | 2018-11-24T10:11:16Z | |
dc.date.issued | 1993-02-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/5955 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/5955 | |
dc.description.abstract | Causal reconstruction is the task of reading a written causal description of a physical behavior, forming an internal model of the described activity, and demonstrating comprehension through question answering. T his task is difficult because written d escriptions often do not specify exactly how r eferenced events fit together. This article (1) ch aracterizes the causal reconstruction problem, (2) presents a representation called transition space, which portrays events in terms of "transitions,'' or collections of changes expressible in everyday language, and (3) describes a program called PATHFINDER, which uses the transition space representation to perform causal reconstruction on simplified English descriptions of physical activity. | en_US |
dc.format.extent | 61 p. | en_US |
dc.format.extent | 548466 bytes | |
dc.format.extent | 2780985 bytes | |
dc.language.iso | en_US | |
dc.subject | knowledge representation | en_US |
dc.subject | explanation | en_US |
dc.subject | causal reasoning | en_US |
dc.subject | sanalogy | en_US |
dc.subject | abstraction | en_US |
dc.subject | natural language | en_US |
dc.title | Causal Reconstruction | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1403.pdf | 2.780Mb | application/pdf | View/ |
AIM-1403.ps.Z | 548.4Kb | application/octet-stream | View/ |