Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Distributed Representation of n-gram Statistics for Boosting Self-organizing Maps with Hyperdimensional Computing
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.ORCID iD: 0000-0002-6032-6155
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.ORCID iD: 0000-0003-0069-640x
La Trobe University, Melbourne, Australia.
Umeå University, Umeå, Sweden.
Show others and affiliations
2019 (English)In: Perspectives of System Informatics: 12th International Andrei P. Ershov Informatics Conference, PSI 2019, Novosibirsk, Russia, July 2–5, 2019, Revised Selected Papers / [ed] Nikolaj Bjørner; Irina Virbitskaite; Andrei Voronkov, Springer, 2019, p. 64-79Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an approach for substantial reduction of the training and operating phases of Self-Organizing Maps in tasks of 2-D projection of multi-dimensional symbolic data for natural language processing such as language classification, topic extraction, and ontology development. The conventional approach for this type of problem is to use n-gram statistics as a fixed size representation for input of Self-Organizing Maps. The performance bottleneck with n-gram statistics is that the size of representation and as a result the computation time of Self-Organizing Maps grows exponentially with the size of n-grams. The presented approach is based on distributed representations of structured data using principles of hyperdimensional computing. The experiments performed on the European languages recognition task demonstrate that Self-Organizing Maps trained with distributed representations require less computations than the conventional n-gram statistics while well preserving the overall performance of Self-Organizing Maps. 

Place, publisher, year, edition, pages
Springer, 2019. p. 64-79
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 11964
Keywords [en]
Self-organizing maps, n-gram statistics, Hyperdimensional computing, Symbol strings
National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
URN: urn:nbn:se:ltu:diva-86147DOI: 10.1007/978-3-030-37487-7_6ISI: 000612725600006Scopus ID: 2-s2.0-85077499893OAI: oai:DiVA.org:ltu-86147DiVA, id: diva2:1575244
Conference
12th International Andrei P. Ershov Informatics Conference (PSI 2019), Novosibirsk, Russia, July 2–5, 2019
Funder
Swedish Research Council, 2015-04677The Swedish Foundation for International Cooperation in Research and Higher Education (STINT), IB2018-7482
Note

ISBN för värdpublikation: 978-3-030-37486-0; 978-3-030-37487-7

Available from: 2021-06-29 Created: 2021-06-29 Last updated: 2021-06-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Kleyko, DenisOsipov, EvgenyVyatkin, Valeriy

Search in DiVA

By author/editor
Kleyko, DenisOsipov, EvgenyVyatkin, Valeriy
By organisation
Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 19 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf