New article published on modeling metaphor using distributional semantics
An article is out from some of us who worked together at Queen Mary University of London: Stephen McGregor, myself, Karolina Rataj (well, not based at QMUL), Matthew Purver, and Geraint Wiggins. Our work is entitled, Re-Representing Metaphor: Modeling Metaphor Perception Using Dynamically Contextual Distributional Semantics. The paper is published in Frontiers in Cognitive Science, and is freely available here. The abstract is below:
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.