Massively Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation*

TLDR

The research develops a natural language processing system that integrates modular knowledge sources with strongly interactive processing. The study presents a parallel model for representing context and priming concepts. Interpretation occurs on a dynamically constructed activation network that resolves ambiguity via a parallel analog relaxation process, and a parallel model represents context and primes concepts. The system yields insights into linguistic phenomena, facilitates hypothesis testing, and demonstrates contextual influence on meaning and semantic garden‑path processing.

Abstract

This is a description of research in developing a natural language processing system with modular knowledge sources but strongly interactive processing. The system offers insights into a variety of linguistic phenomena and allows easy testing of a variety of hypotheses. Language interpretation takes place on a activation network which is dynamically created from input, recent context, and long‐term knowledge. Initially ambiguous and unstable, the network settles on a single interpretation, using a parallel, analog relaxation process. We also describe a parallel model for the representation of context and of the priming of concepts. Examples illustrating contextual influence on meaning interpretation and “semantic garden path” sentence processing, among other issues, are included.