Causal Reconstruction

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/5955

Full metadata record

DC Field	Value	Language
dc.creator	Borchardt, Gary C.	-
dc.date	2004-10-04T14:16:02Z	-
dc.date	2004-10-04T14:16:02Z	-
dc.date	1993-02-01	-
dc.date.accessioned	2013-10-09T02:42:05Z	-
dc.date.available	2013-10-09T02:42:05Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1403	-
dc.identifier	http://hdl.handle.net/1721.1/5955	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	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.	-
dc.format	61 p.	-
dc.format	548466 bytes	-
dc.format	2780985 bytes	-
dc.format	application/octet-stream	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1403	-
dc.subject	knowledge representation	-
dc.subject	explanation	-
dc.subject	causal reasoning	-
dc.subject	sanalogy	-
dc.subject	abstraction	-
dc.subject	natural language	-
dc.title	Causal Reconstruction	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI