The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
N3 Query-By-Structure Approach
|
|
Author(s): Michael Johnson (Wayne State University, USA), Farshad Fotouhi (Wayne State University, USA) and Sorin Draghici (Wayne State University, USA)
Copyright: 2001
Pages: 4
Source title:
Managing Information Technology in a Global Economy
Source Editor(s): Mehdi Khosrow-Pour, D.B.A. (Information Resources Management Association, USA)
DOI: 10.4018/978-1-930708-07-5.ch022
ISBN13: 9781930708075
EISBN13: 9781466665323
|
Abstract
This paper describes our continuing research into a query-by-structure approach. The proposed approach extends existing work, which has focused on querying the Web by content, by allowing the user to request documents containing not only specific content information, but also to specify that documents be of a certain type. We have developed two prototype systems that utilize a supervised Hamming Neural Network and an unsupervised Competitive Neural Network, respectively. Both systems are designed to capture and utilize structure information as well as content during a distributed query on the Web. The primary objective was to test the feasibility of utilizing neural networks to improve document query-by-structure performance. Initial testing has shown promising result when comparing to straight keyword searches.
|
|