Frame identification as categorization: Exemplars vs prototypes in embeddingland

Abstract

Categorization is a central capability of human cognition, and a number of theories have been developed to account for properties of categorization. Despite the fact that many semantic tasks involve categorization, theories of categorization do not play a major role in contemporary research in computational linguistics. This paper follows the idea that embedding-based models of semantics lend themselves well to being formulated in terms of classical categorization theories. The benefit is a group of models that enables (a) the formulation of hypotheses about the impact of major design decisions, and (b) a transparent assessment of these decisions. We instantiate this idea on the frame-semantic frame identification task. We define four models that cross two design variables: (a) the choice of prototype vs. exemplar categorization, corresponding to different degrees of generalization applied to the input, and (b) the presence vs. absence of a fine-tuning step, corresponding to generic vs. task-adaptive categorization. We find that for frame identification, generalization and task-adaptive categorization both yield substantial benefits. Our prototype-based, fine-tuned model, which combines the best choices over these variables, establishes a new state-of-the-art in frame identification.