Parsing embedded clauses with distributed neural networks

Risto Miikkulainen, D. Bijwaard

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

    1 Citation (Scopus)


    A distributed neural network model called SPEC for processing sentences with recursive relative clauses is described. The model is based on separating the tasks of segmenting the input word sequence into clauses, forming the case-role representations, and keeping track of the recursive embeddings into different modules. The system needs to be trained only with the basic sentence constructs, and it generalizes not only to new instances of familiar relative clause structures, but to novel structures as well. SPEC exhibits plausible memory degradation as the depth of the center embeddings increases, its memory is primed by earlier constituents, and its performance is aided by semantic constraints between the constituents. The ability to process structure is largely due to a central executive network that monitors and controls the execution of the entire system. This way, in contrast to earlier subsymbolic systems, parsing is modeled as a controlled high-level process rather than one based on automatic reflex responses.
    Original languageEnglish
    Title of host publicationAAAI'94
    Subtitle of host publicationProceedings of the Twelfth AAAI National Conference on Artificial Intelligence
    PublisherAAAI Press
    Publication statusPublished - 15 Dec 1994
    Event12th AAAI National Conference on Artificial Intelligence 1994 - Seattle, United States
    Duration: 1 Aug 19944 Aug 1994
    Conference number: 12


    Conference12th AAAI National Conference on Artificial Intelligence 1994
    Country/TerritoryUnited States


    • METIS-119294


    Dive into the research topics of 'Parsing embedded clauses with distributed neural networks'. Together they form a unique fingerprint.

    Cite this