Words, Concepts, and the Geometry of Analogy
This work addresses the challenge of improving analogy modeling in computational linguistics and cognitive science, but it appears incremental as it builds on existing geometric theories without claiming major breakthroughs.
The paper tackles the problem of modeling the relationship between words and concepts, particularly analogies in language and cognition, by proposing a geometric approach that uses high-dimensional spaces to project subspaces for solving analogies in a contextualized way.
This paper presents a geometric approach to the problem of modelling the relationship between words and concepts, focusing in particular on analogical phenomena in language and cognition. Grounded in recent theories regarding geometric conceptual spaces, we begin with an analysis of existing static distributional semantic models and move on to an exploration of a dynamic approach to using high dimensional spaces of word meaning to project subspaces where analogies can potentially be solved in an online, contextualised way. The crucial element of this analysis is the positioning of statistics in a geometric environment replete with opportunities for interpretation.