Re-Representing Metaphor: Modeling Metaphor Perception Using Dynamically Contextual Distributional Semantics

TitleRe-Representing Metaphor: Modeling Metaphor Perception Using Dynamically Contextual Distributional Semantics
Publication TypeJournal Article
Year of Publication2019
AuthorsMcGregor S, Agres K, Rataj K, Purver M, Wiggins G
JournalFrontiers in Psychology: Cognitive Science
Date Published04/2019
Type of ArticleOriginal Research
Keywordscomputational creativity, computational linguistics, conceptual models, distributional semantics, metaphor, vector space models

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.