• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation 
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation
    ‌
    ‌

    Browse

    All of QMROCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects
    ‌
    ‌

    Administrators only

    Login
    ‌
    ‌

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation

    View/Open
    Accepted version (446Kb)
    Volume
    6
    Pagination
    55 - 86
    Publisher
    De Gruyter Open
    Publisher URL
    http://www.degruyter.com/view/j/jagi.2015.6.issue-1/jagi-2015-0004/jagi-2015-0004.xml
    DOI
    10.1515/jagi-2015-0004
    Journal
    Journal of Artificial General Intelligence
    Issue
    1
    ISSN
    1946-0163
    Metadata
    Show full item record
    Abstract
    We investigate the relationship between lexical spaces and contextually-defined conceptual spaces, offering applications to creative concept discovery. We define a computational method for discovering members of concepts based on semantic spaces: starting with a standard distributional model derived from corpus co-occurrence statistics, we dynamically select characteristic dimensions associated with seed terms, and thus a subspace of terms defining the related concept. This approach performs as well as, and in some cases better than, leading distributional semantic models on a WordNet-based concept discovery task, while also providing a model of concepts as convex regions within a space with interpretable dimensions. In particular, it performs well on more specific, contextualized concepts; to investigate this we therefore move beyond WordNet to a set of human empirical studies, in which we compare output against human responses on a membership task for novel concepts. Finally, a separate panel of judges rate both model output and human responses, showing similar ratings in many cases, and some commonalities and divergences which reveal interesting issues for computational concept discovery.
    Authors
    McGregor, S; Agres, K; Purver, M; Wiggins, G
    URI
    http://qmro.qmul.ac.uk/xmlui/handle/123456789/11291
    Collections
    • Electronic Engineering and Computer Science [2358]
    Copyright statements
    Copyright: 2015. The authors
    Twitter iconFollow QMUL on Twitter
    Twitter iconFollow QM Research
    Online on twitter
    Facebook iconLike us on Facebook
    • Site Map
    • Privacy and cookies
    • Disclaimer
    • Accessibility
    • Contacts
    • Intranet
    • Current students

    Modern Slavery Statement

    Queen Mary University of London
    Mile End Road
    London E1 4NS
    Tel: +44 (0)20 7882 5555

    © Queen Mary University of London.