| Abstract
|
The CALO system will include an end to end … The CALO system will include an end to end system capability that will allow CALO to provide explanations for its answers. This document focuses on explanations for task-oriented processing within the CALO system and describes a set of types of questions and answers. We include a set of general categories of task-oriented questions and answers.The questions and answers are instance of more general patterns which are also described. In order to provide concrete examples, we introduce a demo scenario concerned with laptop purchasing. Our specific example questions and answers utilize this scenario. We also include alternative answers so that we can describe a spectrum of answers and our approaches to providing these answers. We present an architecture for task-oriented explanation generation within CALO. Next we describe our strategy for interacting with the SPARK system in order to obtain the required information.Finally, we provide a view of task execution as inference. ide a view of task execution as inference.
|
| Author
|
Deborah L. McGuinness +,
Paulo Pinheiro da Silva +,
Michael Wolverton +
|
| Bibtype
|
techreport +
|
| Institution
|
Knowledge Systems, AI Laboratory, Stanford University +
|
| Key
|
KSL-05-11 +
|
| Modification dateThis property is a special property in this wiki.
|
1 May 2009 13:35:38 +
|
| Number
|
KSL-05-11 +
|
| Paper
|
KSL-05-11.pdf +
|
| Tag
|
Computer science +
|
| Title
|
Plan for Explaining Task Execution in CALO +
|
| Tr id
|
KSL-05-11 +
|
| Year
|
2005 +
|
| Categories |
Technical Report,
Publication,
KSL Technical Report
|
