• Login
    View Item 
    •   Maryland Shared Open Access Repository Home
    • ScholarWorks@UMBC
    • UMBC College of Engineering and Information Technology
    • UMBC Computer Science and Electrical Engineering Department
    • View Item
    •   Maryland Shared Open Access Repository Home
    • ScholarWorks@UMBC
    • UMBC College of Engineering and Information Technology
    • UMBC Computer Science and Electrical Engineering Department
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Unsupervised Selection of Negative Examples for Grounded Language Learning

    Thumbnail
    Files
    PillaiMatuszekAAAI2018NegativeExamples.pdf (3.668Mb)
    Links to Files
    https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17440
    Permanent Link
    http://hdl.handle.net/11603/11241
    Collections
    • UMBC Computer Science and Electrical Engineering Department
    • UMBC Faculty Collection
    Metadata
    Show full item record
    Author/Creator
    Pillai, Nisha
    Matuszek, Cynthia
    Date
    2018-02
    Type of Work
    9 pages
    Text
    conference papers and proceedings preprints
    Citation of Original Publication
    Nisha Pillai, Cynthia Matuszek, Unsupervised Selection of Negative Examples for Grounded Language Learning, Thirty-Second AAAI Conference on Artificial Intelligence , 2018, https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17440
    Rights
    This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please contact the author.
    Subjects
    robotics
    human-robot-interaction
    natural-language-processing
    Interactive Robotics and Language Lab
    Abstract
    There has been substantial work in recent years on grounded language acquisition, in which language and sensor data are used to create a model relating linguistic constructs to the perceivable world. While powerful, this approach is frequently hindered by ambiguities, redundancies, and omissions found in natural language. We describe an unsupervised system that learns language by training visual classifiers, first selecting important terms from object descriptions, then automatically choosing negative examples from a paired corpus of perceptual and linguistic data. We evaluate the effectiveness of each stage as well as the system's performance on the overall learning task.


    Albin O. Kuhn Library & Gallery
    University of Maryland, Baltimore County
    1000 Hilltop Circle
    Baltimore, MD 21250
    www.umbc.edu/scholarworks

    Contact information:
    Email: scholarworks-group@umbc.edu
    Phone: 410-455-3021


    If you wish to submit a copyright complaint or withdrawal request, please email mdsoar-help@umd.edu.

     

     

    My Account

    LoginRegister

    Browse

    This CollectionBy Issue DateTitlesAuthorsSubjectsType

    Statistics

    View Usage Statistics


    Albin O. Kuhn Library & Gallery
    University of Maryland, Baltimore County
    1000 Hilltop Circle
    Baltimore, MD 21250
    www.umbc.edu/scholarworks

    Contact information:
    Email: scholarworks-group@umbc.edu
    Phone: 410-455-3021


    If you wish to submit a copyright complaint or withdrawal request, please email mdsoar-help@umd.edu.