Having Your Cake and Eating It Too: Autonomy and Interaction in a Model of Sentence Processing

TL;DR

This paper proposes a hybrid model of sentence processing that combines a unified processor with separate knowledge sources, aiming to reconcile conflicting views and advance toward human-like language understanding.

Contribution

It introduces the COMPERE computational model, demonstrating the feasibility of integrating a single processor with multiple knowledge sources in language processing.

Findings

The hybrid model explains diverse data sets effectively.

COMPERE demonstrates the viability of combined processing and knowledge sources.

The approach bridges the gap between modular and unified models.

Abstract

Is the human language understander a collection of modular processes operating with relative autonomy, or is it a single integrated process? This ongoing debate has polarized the language processing community, with two fundamentally different types of model posited, and with each camp concluding that the other is wrong. One camp puts forth a model with separate processors and distinct knowledge sources to explain one body of data, and the other proposes a model with a single processor and a homogeneous, monolithic knowledge source to explain the other body of data. In this paper we argue that a hybrid approach which combines a unified processor with separate knowledge sources provides an explanation of both bodies of data, and we demonstrate the feasibility of this approach with the computational model called COMPERE. We believe that this approach brings the language processing community significantly closer to offering human-like language processing systems.