Retrieving Semantically Distant Analogies with Knowledge-Directed Spreading Activation

From Tetherless World Wiki

Jump to: navigation, search

Citation: Michael Wolverton and Barbara Hayes-Roth. (1994) Retrieving Semantically Distant Analogies with Knowledge-Directed Spreading Activation. In KSL-94-19, 1994.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Michael Wolverton and Barbara Hayes-Roth
title Retrieving Semantically Distant Analogies with Knowledge-Directed Spreading Activation
number KSL-94-19
institution Knowledge Systems, AI Laboratory
address Seattle, Washington
year 1994
Bibtex more
note Updated July.
Access Paper
abstract Techniques that traditionally have been useful for retrievingsame-domain analogies from small single-use knowledge bases, such asspreading activation and indexing on selected features, are inadequatefor retrieving cross-domain analogies from large multi-use knowledgebases. In this paper, we describe Knowledge-Directed SpreadingActivation (KDSA), a new method for retrieving analogies in a largesemantic network. KDSA uses task-specific knowledge to guide aspreading activation search to a case or concept in memory that meetsa desired similarity condition. Specifically, KDSA exploitsevaluations of near-analogies encountered during the search to directthe search toward progressively more promising analogies. We describea specific instantiation of this method for the task of innovativedesign, and we summarize the theoretical and experimental results usedto validate KDSA.

KSL Technical Report ID: KSL-94-19
Facts about Retrieving Semantically Distant Analogies with Knowledge-Directed Spreading ActivationRDF feed
Abstract Techniques that traditionally have been us … Techniques that traditionally have been useful for retrievingsame-domain analogies from small single-use knowledge bases, such asspreading activation and indexing on selected features, are inadequatefor retrieving cross-domain analogies from large multi-use knowledgebases. In this paper, we describe Knowledge-Directed SpreadingActivation (KDSA), a new method for retrieving analogies in a largesemantic network. KDSA uses task-specific knowledge to guide aspreading activation search to a case or concept in memory that meetsa desired similarity condition. Specifically, KDSA exploitsevaluations of near-analogies encountered during the search to directthe search toward progressively more promising analogies. We describea specific instantiation of this method for the task of innovativedesign, and we summarize the theoretical and experimental results usedto validate KDSA. experimental results usedto validate KDSA.
Address Seattle, Washington  +
Author Michael Wolverton and Barbara Hayes-Roth  +
Bibtype techreport  +
Has author Michael Wolverton and Barbara Hayes-Roth  +
Has identifier KSL-94-19  +
Has publishing details 1994  +
Has title Retrieving Semantically Distant Analogies with Knowledge-Directed Spreading Activation  +
Has where published KSL-94-19  +
Has year 1994  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-94-19  +
Note Updated July.
Number KSL-94-19  +
Process note YES  +
Title Retrieving Semantically Distant Analogies with Knowledge-Directed Spreading Activation  +
Year 1994  +
Retrieved from "http://tw.rpi.edu/wiki/Retrieving_Semantically_Distant_Analogies_with_Knowledge-Directed_Spreading_Activation"
Personal tools