A pervasive, yet much ignored, factor in the analysis of processing-fa ilures is the problem of misor ganized knowledge. If a system’ s knowledge is not indexed or organized correctly, it may make an error, not because it does not have either the general capability or specific knowledge to solve a problem, but rather because it does not have the knowledge sufficiently organized so that the appropriate knowledge structures are brought to bear on the problem at the appropriate time. In such cases, the system can be said to have “forgotten” the knowledge, if only in this context. This is the problem of for getting or retrieval failure. This research presents an analysis along with a declarative representation of a number of types of for getting errors. Such representations can extend the capability of introspective failure-driven learning systems, allowing them to reduce the likelihood of repeating such errors. Examples are presented from the Meta-AQUA program, which learns to improve its performance on a story understanding task through an introspective meta-analysis of its knowledge, its or ganization of its knowledge, and its reasoning processes.
[1]
R. Schank,et al.
A Content Theory of Memory Indexing
,
1990
.
[2]
Roger C. Schank,et al.
Dynamic memory - a theory of reminding and learning in computers and people
,
1983
.
[3]
Lawrence Birnbaum,et al.
Opportunistic Planning and Freudian Slips
,
1992
.
[4]
Shaul Markovitch,et al.
The Role of Forgetting in Learning
,
1988,
ML.
[5]
Ashwin Ram,et al.
A Theory of Questions and Question Asking
,
1991
.
[6]
C SchankRoger,et al.
Dynamic Memory: A Theory of Reminding and Learning in Computers and People
,
1983
.
[7]
Jon Doyle,et al.
A Truth Maintenance System
,
1979,
Artif. Intell..
[8]
Drew McDermott,et al.
A General Framework for Reason Maintenance
,
1991,
Artif. Intell..
[9]
Janet L. Kolodner,et al.
Retrieval and organizational strategies in conceptual memory: a computer model
,
1980
.
[10]
James L. McClelland,et al.
A distributed model of human learning and memory
,
1986
.
[11]
Ashwin Ram,et al.
Multistrategy Learning with Introspective Meta-Explanations
,
1992,
ML.