Keywords

Soar, WordNet, word-sense disambiguation, syntax/semantics interface, cognitive modeling

Abstract

This paper explores issues of psychological plausibility in modeling natural language understanding within Soar, a symbolic cognitive model. It focuses on constructing syntactic and semantic representations in simulated real time, with particular emphasis on word sense disambiguation (WSD). We discuss (i) what level of WSD should be modeled and (ii) how to use resources such as WordNet to inform these models. A preliminary model of coarse-grained WSD is included to show how syntactic, semantic, and other knowledge sources interact in Soar. Finally, we explore issues of interleaving, learning, and integrating other WSD approaches with Soar's native model of learning.

Original Publication Citation

C. Anton Rytting and Deryle Lonsdale (2001). An Operator-based Account of Semantic Processing; The Acquisition and Representation of Word Meaning; European Summer School for Logic, Language, and Information; pp. 84-92.