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

• Main Authors: Stephen McGregor, Kat Agres, Karolina Rataj, Matthew Purver, Geraint Wiggins
• Format: Article
• Language: English
• Published: Frontiers Media S.A. 2019-04-01
• Series: Frontiers in Psychology
• Subjects: distributional semantics; metaphor; conceptual models; computational creativity; vector space models; computational linguistics
• Online Access: https://www.frontiersin.org/article/10.3389/fpsyg.2019.00765/full

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.