Automatic subject indexing using an associative neural network

Y. M. Chung, W. M. Pottenger, Bruce R Schatz

Research output: Contribution to conferencePaper

Abstract

The global growth in popularity of the World Wide Web has been enabled in part by the availability of browser based search tools which in turn have led to an increased demand for indexing techniques and technologies. As the amount of globally accessible information in community repositories grows, it is no longer cost-effective for such repositories to be indexed by professional indexers who have been trained to be consistent in subject assignment from controlled vocabulary lists. The era of amateur indexers is thus upon us, and the information infrastructure needs to provide support for such indexing if search of the Net is to produce useful results. In this paper, we propose the Concept Assignor, an automatic subject indexing system based on a variant of the Hopfield network [13]. In the application discussed herein, a collection of documents is used to automatically create a subset of a thesaurus termed a Concept Space [4]. To automatically index an individual document, concepts extracted from the given document become the input pattern to a Concept Space represented as a Hopfield network. The Hopfield net parallel spreading activation process produces another set of concepts that are strongly related to the concepts of the input document. Such concepts are suitable for use in an interactive indexing environment. A prototype of our automatic subject indexing system has been implemented as part of the Interspace, a semantic indexing and retrieval environment which supports statistically-based semantic indexing in a persistent object environment.

Original languageEnglish (US)
Pages59-68
Number of pages10
StatePublished - Jan 1 1998
EventProceedings of the 1998 3rd ACM Conference on Digital Libraries - Pittsburgh, PA, USA
Duration: Jun 23 1998Jun 26 1998

Other

OtherProceedings of the 1998 3rd ACM Conference on Digital Libraries
CityPittsburgh, PA, USA
Period6/23/986/26/98

Fingerprint

Automatic indexing
Thesauri
indexing
neural network
Semantics
Neural networks
World Wide Web
Chemical activation
Availability
Costs
semantics
thesaurus
amateur
activation
popularity
vocabulary
infrastructure
Internet
demand

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Cite this

Chung, Y. M., Pottenger, W. M., & Schatz, B. R. (1998). Automatic subject indexing using an associative neural network. 59-68. Paper presented at Proceedings of the 1998 3rd ACM Conference on Digital Libraries, Pittsburgh, PA, USA, .

Automatic subject indexing using an associative neural network. / Chung, Y. M.; Pottenger, W. M.; Schatz, Bruce R.

1998. 59-68 Paper presented at Proceedings of the 1998 3rd ACM Conference on Digital Libraries, Pittsburgh, PA, USA, .

Research output: Contribution to conferencePaper

Chung, YM, Pottenger, WM & Schatz, BR 1998, 'Automatic subject indexing using an associative neural network' Paper presented at Proceedings of the 1998 3rd ACM Conference on Digital Libraries, Pittsburgh, PA, USA, 6/23/98 - 6/26/98, pp. 59-68.
Chung YM, Pottenger WM, Schatz BR. Automatic subject indexing using an associative neural network. 1998. Paper presented at Proceedings of the 1998 3rd ACM Conference on Digital Libraries, Pittsburgh, PA, USA, .
Chung, Y. M. ; Pottenger, W. M. ; Schatz, Bruce R. / Automatic subject indexing using an associative neural network. Paper presented at Proceedings of the 1998 3rd ACM Conference on Digital Libraries, Pittsburgh, PA, USA, .10 p.
@conference{04e01469390f4f15bf9f74f49afc486d,
title = "Automatic subject indexing using an associative neural network",
abstract = "The global growth in popularity of the World Wide Web has been enabled in part by the availability of browser based search tools which in turn have led to an increased demand for indexing techniques and technologies. As the amount of globally accessible information in community repositories grows, it is no longer cost-effective for such repositories to be indexed by professional indexers who have been trained to be consistent in subject assignment from controlled vocabulary lists. The era of amateur indexers is thus upon us, and the information infrastructure needs to provide support for such indexing if search of the Net is to produce useful results. In this paper, we propose the Concept Assignor, an automatic subject indexing system based on a variant of the Hopfield network [13]. In the application discussed herein, a collection of documents is used to automatically create a subset of a thesaurus termed a Concept Space [4]. To automatically index an individual document, concepts extracted from the given document become the input pattern to a Concept Space represented as a Hopfield network. The Hopfield net parallel spreading activation process produces another set of concepts that are strongly related to the concepts of the input document. Such concepts are suitable for use in an interactive indexing environment. A prototype of our automatic subject indexing system has been implemented as part of the Interspace, a semantic indexing and retrieval environment which supports statistically-based semantic indexing in a persistent object environment.",
author = "Chung, {Y. M.} and Pottenger, {W. M.} and Schatz, {Bruce R}",
year = "1998",
month = "1",
day = "1",
language = "English (US)",
pages = "59--68",
note = "Proceedings of the 1998 3rd ACM Conference on Digital Libraries ; Conference date: 23-06-1998 Through 26-06-1998",

}

TY - CONF

T1 - Automatic subject indexing using an associative neural network

AU - Chung, Y. M.

AU - Pottenger, W. M.

AU - Schatz, Bruce R

PY - 1998/1/1

Y1 - 1998/1/1

N2 - The global growth in popularity of the World Wide Web has been enabled in part by the availability of browser based search tools which in turn have led to an increased demand for indexing techniques and technologies. As the amount of globally accessible information in community repositories grows, it is no longer cost-effective for such repositories to be indexed by professional indexers who have been trained to be consistent in subject assignment from controlled vocabulary lists. The era of amateur indexers is thus upon us, and the information infrastructure needs to provide support for such indexing if search of the Net is to produce useful results. In this paper, we propose the Concept Assignor, an automatic subject indexing system based on a variant of the Hopfield network [13]. In the application discussed herein, a collection of documents is used to automatically create a subset of a thesaurus termed a Concept Space [4]. To automatically index an individual document, concepts extracted from the given document become the input pattern to a Concept Space represented as a Hopfield network. The Hopfield net parallel spreading activation process produces another set of concepts that are strongly related to the concepts of the input document. Such concepts are suitable for use in an interactive indexing environment. A prototype of our automatic subject indexing system has been implemented as part of the Interspace, a semantic indexing and retrieval environment which supports statistically-based semantic indexing in a persistent object environment.

AB - The global growth in popularity of the World Wide Web has been enabled in part by the availability of browser based search tools which in turn have led to an increased demand for indexing techniques and technologies. As the amount of globally accessible information in community repositories grows, it is no longer cost-effective for such repositories to be indexed by professional indexers who have been trained to be consistent in subject assignment from controlled vocabulary lists. The era of amateur indexers is thus upon us, and the information infrastructure needs to provide support for such indexing if search of the Net is to produce useful results. In this paper, we propose the Concept Assignor, an automatic subject indexing system based on a variant of the Hopfield network [13]. In the application discussed herein, a collection of documents is used to automatically create a subset of a thesaurus termed a Concept Space [4]. To automatically index an individual document, concepts extracted from the given document become the input pattern to a Concept Space represented as a Hopfield network. The Hopfield net parallel spreading activation process produces another set of concepts that are strongly related to the concepts of the input document. Such concepts are suitable for use in an interactive indexing environment. A prototype of our automatic subject indexing system has been implemented as part of the Interspace, a semantic indexing and retrieval environment which supports statistically-based semantic indexing in a persistent object environment.

UR - http://www.scopus.com/inward/record.url?scp=0031637994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031637994&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0031637994

SP - 59

EP - 68

ER -