Learning the Past Tense of English Verbs: The Symbolic Pattern Associator vs. Connectionist Models

TL;DR

This paper compares symbolic and connectionist models for learning English past tense, finding that the Symbolic Pattern Associator outperforms neural networks in generalizing to unseen verbs, with implications for cognitive modeling.

Contribution

Introduces a Symbolic Pattern Associator based on decision-tree learning and demonstrates its superior generalization over neural networks in past tense verb learning.

Findings

SPA outperforms ANNs in generalizing to unseen verbs

Decision-tree based models offer better insights into language acquisition

Discussion of a new default strategy for decision-tree learning

Abstract

Learning the past tense of English verbs - a seemingly minor aspect of language acquisition - has generated heated debates since 1986, and has become a landmark task for testing the adequacy of cognitive modeling. Several artificial neural networks (ANNs) have been implemented, and a challenge for better symbolic models has been posed. In this paper, we present a general-purpose Symbolic Pattern Associator (SPA) based upon the decision-tree learning algorithm ID3. We conduct extensive head-to-head comparisons on the generalization ability between ANN models and the SPA under different representations. We conclude that the SPA generalizes the past tense of unseen verbs better than ANN models by a wide margin, and we offer insights as to why this should be the case. We also discuss a new default strategy for decision-tree learning algorithms.