Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Distributed representation of n-gram statistics for boosting self-organizing maps with hyperdimensional computing
Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.ORCID-id: 0000-0002-1313-0934
Visa övriga samt affilieringar
2019 (Engelska)Ingår i: Perspectives of system informatics / [ed] Nikolaj Bjørner, Irina Virbitskaite, Andrei Voronkov, Cham: Springer, 2019, s. 64-79Konferensbidrag, Publicerat paper (Refereegranskat)
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.

Ort, förlag, år, upplaga, sidor
Cham: Springer, 2019. s. 64-79
Serie
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 11964
Nyckelord [en]
Self-organizing maps, n-gram statistics, Hyperdimensional computing, Symbol strings
Nationell ämneskategori
Språkteknologi (språkvetenskaplig databehandling)
Identifikatorer
URN: urn:nbn:se:umu:diva-169610DOI: 10.1007/978-3-030-37487-7_6ISI: 000612725600006Scopus ID: 2-s2.0-85077499893ISBN: 978-3-030-37486-0 (tryckt)ISBN: 978-3-030-37487-7 (digital)OAI: oai:DiVA.org:umu-169610DiVA, id: diva2:1422893
Konferens
12th International Andrei P. Ershov Informatics Conference, PSI 2019, Novosibirsk, Russia, July 2–5, 2019
Tillgänglig från: 2020-04-09 Skapad: 2020-04-09 Senast uppdaterad: 2023-09-05Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Wiklund, Urban

Sök vidare i DiVA

Av författaren/redaktören
Wiklund, Urban
Av organisationen
Radiofysik
Språkteknologi (språkvetenskaplig databehandling)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 320 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf