Re-representing metaphor: Modeling metaphor perception using dynamically contextual distributional semantics

Stephen McGregor*, Kat Agres, Karolina Rataj, Matthew Purver, Geraint Wiggins

*Corresponding author for this work

    Research output: Contribution to journalArticleAcademicpeer-review

    2 Citations (Scopus)
    2 Downloads (Pure)

    Abstract

    In this paper, we present a novel context-dependent approach to modeling word meaning, and apply it to the modeling of metaphor. In distributional semantic approaches, words are represented as points in a high dimensional space generated from co-occurrence statistics; the distances between points may then be used to quantifying semantic relationships. Contrary to other approaches which use static, global representations, our approach discovers contextualized representations by dynamically projecting low-dimensional subspaces; in these ad hoc spaces, words can be re-represented in an open-ended assortment of geometrical and conceptual configurations as appropriate for particular contexts. We hypothesize that this context-specific re-representation enables a more effective model of the semantics of metaphor than standard static approaches. We test this hypothesis on a dataset of English word dyads rated for degrees of metaphoricity, meaningfulness, and familiarity by human participants. We demonstrate that our model captures these ratings more effectively than a state-of-the-art static model, and does so via the amount of contextualizing work inherent in the re-representational process.

    Original languageEnglish
    Article number765
    JournalFrontiers in psychology
    Volume10
    Issue numberMAR
    DOIs
    Publication statusPublished - 2019

    Keywords

    • Computational creativity
    • Computational linguistics
    • Conceptual models
    • Distributional semantics
    • Metaphor
    • Vector space models

    Fingerprint

    Dive into the research topics of 'Re-representing metaphor: Modeling metaphor perception using dynamically contextual distributional semantics'. Together they form a unique fingerprint.

    Cite this