skip to main content
10.3115/1072017.1072045dlproceedingsArticle/Chapter ViewAbstractPublication PagesmucConference Proceedingsconference-collections
Article
Free access

USC: description of the SNAP system used for MUC-5

Published: 25 August 1993 Publication History

Abstract

The SNAP information extraction system has been developed as a part of a three-year SNAP project sponsored by the National Science Foundation. The main goal of the SNAP project is to build a massively parallel computer capable of fast and accurate natural language processing [5]. Throughout the project, a parallel computer was built in the Parallel Knowledge Processing Laboratory at USC, and various software was developed to operate the machine [3]. The approach in designing SNAP was to find a knowledge representation and a reasoning paradigm useful for natural language processing which exhibits massive parallelism. We have selected marker-passing on semantic networks as a way to represent and process linguistic knowledge.

References

[1]
Cha S. and Moldovan D., "A Marker-Passing Algorithm for Reference Resolution," Proceedings of IEEE International Conference on Tools with Artificial Intelligence, 1993.
[2]
Chung, M. and Moldovan, D., "Memory-Based Parsing with Integrated Syntactic and Semantic Analysis on SNAP", Technical Report PKPL 91-10, Dept. of Electrical Engineering-Systems, University of Southern California, 1991.
[3]
DeMara, R. and Moldovan, D., "The SNAP-1 Parallel AI Prototype", Proceedings of Annual International Symposium on Computer Architecture, 1991.
[4]
Kim, J.-T. and Moldovan, D., "Acquisition of semantic patterns for information extraction from corpora," Proceedings of CAIA-93, the Ninth IEEE Conference on AI Applications, 1993.
[5]
Moldovan, D., Lee, W., Lin, C., and Chung, M., "SNAP: Parallel Processing Applied to AI", IEEE Computer, May 1992.
[6]
Riesbeck, C. and Martin, C., "Direct Memory Access Parsing," Report 354, Dept. of Computer Science, Yale University, 1985.
[7]
Sundheim B., editor, Proceedings of the Fourth Message Understanding Conference (MUC-4), Morgan Kaufmann Publishers, Inc., San Mateo, Ca, June 1992.

Cited By

View all
  • (2000)Using WordNet and Lexical Operators to Improve Internet SearchesIEEE Internet Computing10.1109/4236.8158474:1(34-43)Online publication date: 1-Jan-2000

Recommendations

Comments

Information & Contributors

Information

Published In

cover image DL Hosted proceedings
MUC5 '93: Proceedings of the 5th conference on Message understanding
August 1993
390 pages
ISBN:1558603360

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 25 August 1993

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)80
  • Downloads (Last 6 weeks)14
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2000)Using WordNet and Lexical Operators to Improve Internet SearchesIEEE Internet Computing10.1109/4236.8158474:1(34-43)Online publication date: 1-Jan-2000

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media