Learning to Refine Case Libraries: Initial Results
D. Aha, and L. Breslow. ECML-97 MLNet Workshop Notes. Case-Based Learning: Beyond Classification of Feature Vectors, page 9--16. Naval Research Laboratory, Washington, D. C., USA, Navy Center for Applied Research in Artificial Intelligence, (1997)
Abstract
Conversational case-based reasoning (CBR) systems, which
incrementally extract a query description through a user-directed
conversation, are advertised for their ease of use. However,
designing large case libraries that have good performance (i.e.\
precision and querying efficiency) is difficult. CBR vendors
provide guidelines for designing these libraries manually, but
the guidelines are difficult to apply. We describe an automated
inductive approach that revises conversational case libraries to
increase their conformance with design guidelines. Revision
increased performance on three conversational case libraries.
%0 Conference Paper
%1 AhaBreslow97
%A Aha, David W.
%A Breslow, Leonard A.
%B ECML-97 MLNet Workshop Notes. Case-Based Learning: Beyond Classification of Feature Vectors
%C Naval Research Laboratory, Washington, D. C., USA
%D 1997
%E Wettschereck, Dietrich
%E Aha, David W.
%I Navy Center for Applied Research in Artificial Intelligence
%K Case-Based Reasoning, Conversational Maintenance
%P 9--16
%T Learning to Refine Case Libraries: Initial Results
%X Conversational case-based reasoning (CBR) systems, which
incrementally extract a query description through a user-directed
conversation, are advertised for their ease of use. However,
designing large case libraries that have good performance (i.e.\
precision and querying efficiency) is difficult. CBR vendors
provide guidelines for designing these libraries manually, but
the guidelines are difficult to apply. We describe an automated
inductive approach that revises conversational case libraries to
increase their conformance with design guidelines. Revision
increased performance on three conversational case libraries.
@inproceedings{AhaBreslow97,
abstract = {Conversational case-based reasoning (CBR) systems, which
incrementally extract a query description through a user-directed
conversation, are advertised for their ease of use. However,
designing large case libraries that have good performance (i.e.\
precision and querying efficiency) is difficult. CBR vendors
provide guidelines for designing these libraries manually, but
the guidelines are difficult to apply. We describe an automated
inductive approach that revises conversational case libraries to
increase their conformance with design guidelines. Revision
increased performance on three conversational case libraries.},
added-at = {2006-11-14T09:19:23.000+0100},
address = {Naval Research Laboratory, Washington, D. C., USA},
author = {Aha, David W. and Breslow, Leonard A.},
biburl = {https://www.bibsonomy.org/bibtex/2d83da7f13dd5c71a8b697c7ed6d4eb76/thorob67},
booktitle = {{ECML}-97 {MLNet} Workshop Notes. Case-Based Learning: Beyond Classification of Feature Vectors},
editor = {Wettschereck, Dietrich and Aha, David W.},
interhash = {af6a31e630a11985da5923775cb27419},
intrahash = {d83da7f13dd5c71a8b697c7ed6d4eb76},
keywords = {Case-Based Reasoning, Conversational Maintenance},
pages = {9--16},
publisher = {Navy Center for Applied Research in Artificial Intelligence},
timestamp = {2006-11-14T09:19:23.000+0100},
title = {Learning to Refine Case Libraries: Initial Results},
year = 1997
}