Year: 2006
Type: article
Abstract: We present a model of human sentence processing that extends a standard probabilistic grammar model with a semantic mod-ule which computes the thematic fit of verbs and arguments in a cognitively plausible way. Our model differs from existing probabilistic accounts (e.g., Jurafsky, 1996) by capturing both syntactic and semantic influences in human sentence process-ing. It also overcomes limitations of constraint-based mod-els (Spivey-Knowlton, 1996; Narayanan and Jurafsky, 2002), as its parameters can be acquired automatically from corpus data, and no hand-coding of constraints is required. We evalu-ate our semantic module against human ratings of thematic fit, and also test the complete model’s performance for two well-studied ambiguities from the sentence processing literature.
Authors: Matthew Croker, Frank Keller, Ulrike Padó
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2184008231