• Login
    View Item 
    •   Athenaeum Home
    • Institute for Artificial Intelligence
    • CASPR Research Reports
    • View Item
    •   Athenaeum Home
    • Institute for Artificial Intelligence
    • CASPR Research Reports
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Instantiating thematic roles with a recurrent neural network

    Thumbnail
    View/Open
    ai199301.pdf (81.31Kb)
    ai199301.ps (567.7Kb)
    Date
    1993
    Author
    Eisenhart, F. James
    Metadata
    Show full item record
    Abstract
    Human languages have both a surface structure and a deep structure. The surface structure of a language can be described by grammatical rules which generate its well-formed sentences. Deep structure can be described by a set of thematic roles which specify the meaning of a sentence independent of any particular language. In this paper, I show that a recurrent neural network can learn to map English sentences generated by a unification-based grammar onto their appropriate thematic roles. Two models are evaluated: (1) a simple recurrent network like those of Jordan (1986) and Elman (1990), and (2) a modified recurrent network which incorporates a time-varying training signal, direct connections between its input and output units, and two separate state layers. It is found that the modified network learns faster and more completely than the simple recurrent network.
    URI
    http://hdl.handle.net/10724/30206
    Collections
    • CASPR Research Reports

    About Athenaeum | Contact Us | Send Feedback
     

     

    Browse

    All of AthenaeumCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    About Athenaeum | Contact Us | Send Feedback