An Extended Kohonen Feature Map for Sentence Recognition

Aarnoud Hoekstra, Marc F.J. Drossaers

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    In this paper an extended Kohonen feature map is proposed that is able to store sequences of input patterns. The extended map is used in a natural language application: the recognition of sentences produced by a regular grammar. This network is able to learn to simulate a finite-state machine for the grammar, given examples of legal sentences from the grammar.
    Original languageEnglish
    Title of host publicationICANN ’93
    Subtitle of host publicationProceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993
    EditorsStan Gielen, Bert Kappen
    Place of PublicationLondon
    PublisherSpringer
    Pages404-407
    ISBN (Electronic)978-1-4471-2063-6
    ISBN (Print)978-3-540-19839-0
    DOIs
    Publication statusPublished - 30 Jan 1993
    EventInternational Conference on Artificial Neural Networks, ICANN 1993 - Amsterdam, Netherlands
    Duration: 13 Sep 199316 Sep 1993

    Conference

    ConferenceInternational Conference on Artificial Neural Networks, ICANN 1993
    Abbreviated titleICANN
    CountryNetherlands
    CityAmsterdam
    Period13/09/9316/09/93

    Keywords

    • Natural language processing
    • Input pattern
    • Winning neuron
    • Natural language processing task
    • Sentence recognition

    Fingerprint

    Dive into the research topics of 'An Extended Kohonen Feature Map for Sentence Recognition'. Together they form a unique fingerprint.

    Cite this