On learning the past-tenses of English verbs: implicit rules or parallel distributed processing

@inproceedings{Rumelhart1986OnLT,
  title={On learning the past-tenses of English verbs: implicit rules or parallel distributed processing},
  author={David E. Rumelhart and James L. McClelland},
  year={1986}
}
Abstract : This paper presents an alternative to the standard rule based account of a child's acquisition of the past tense in English. [] Key Method We show that the acquisition data can be accounted for in more detail by dispensing with the assumption that the child learns rules and substituting in its place a simple homogeneous learning procedure. We show how rule-like behavior can emerge from the interactions among a network of units encoding the root form to past tense mapping. A large computer…
Rules vs. analogy in English past tenses: a computational/experimental study
Implicit vs. explicit learning in German noun plurals
Over the past few decades there has been a lot of debate, about language learning and the opinion about the status of mental rule during the process of language learning is still divided between
Representing Regularity: The English Past Tense
TLDR
The purpose here is to investigate whether representational differences between regular and irregular verbs can be accounted for by a single mechanism, connectionist model.
Networks that Learn about Phonological Feature Persistence
TLDR
Two experiments investigating the power of simple recurrent networks to acquire phonological regularities that can be described in terms of the persistence of particular features show that an SRN is capable of learning patterns of feature persistence across morpheme boundaries.
Learning the Past Tense of English Verbs: Connectionism Fights Back
TLDR
This paper shows that the conclusion that the SPA generalizes the past tense of unseen verbs better than ANN models by a wide margin was based on comparisons with an uncharacteristically poorly performing ANN.
Learning a morphological system without a default: the Polish genitive
TLDR
This paper contrasts the acquisition of the English past tense inflection with a much more complex morphological subsystem, the Polish genitive, and argues that in the latter two cases, the default-like character of one of the affixes is attributable to the properties of the relevant inflectional subsystems, not to the predispositions that children bring to the language-learning task.
Connectionist Rules of Language
TLDR
A modular connectionist network is described that learns the German verb paradigm and generalizes to novel verbs in ways that correspond to empirical data and is seen as evidence that emergent linguistic rules need not be implemented as rules in the brain.
...
...

References

SHOWING 1-10 OF 26 REFERENCES
The Child's Learning of English Morphology
In this study we set out to discover what is learned by children exposed to English morphology. To test for knowledge of morphological rules, we use nonsense materials. We know that if the subject
Rules and schemas in the development and use of the English past tense
Consistent error patterns in English past-tense forms are reported for three age groups: preschoolers, 8-10-year-olds, and adults. It is argued that, although irregular forms are rote-learned,
Simulating a Skilled Typist: A Study of Skilled Cognitive-Motor Performance
TLDR
A model for the control of the hands and fingers during typing based upon an Activation-Trigger-Schema system in which a hierarchical structure of schemata directs the selection of the letters to be typed and, then, controls the hand and finger movements by a cooperative, relaxation algorithm.
An Interactive Activation Model of the Effect of Context in Perception. Part 2
TLDR
A number of new experiments are presented, designed to assess the roles of direct and indirect evidence concerning the identity of a letter in an input string and a number of extensions of the model are proposed to account for aspects of word perception currently ignored.
Natural Artificial Languages: Low Level Processes
  • G. Perlman
  • Computer Science
    Int. J. Man Mach. Stud.
  • 1984
Harmony Theory: A Mathematical Framework for Stochastic Parallel Processing.
TLDR
As this temperature is lowered, the system appears to display a dramatic tendency to coherently interpret input, even if the evidence for any particular interpretation is very weak.
Harmony Theory: Problem Solving, Parallel Cognitive Models, and Thermal Physics.
Abstract : The first paper describes a parallel model designed to solve a class of relatively simple problems from elementary physics, and discusses the implications for models of problem solving in
Five Papers on Human-Machine Interaction.
TLDR
This report consists of five brief papers on different aspects of human-machine interaction, including the role of a person's mental model in the interaction with systems and how analysis of error can lead to design principles.
Representation in Memory.
TLDR
Major controversies within psychology -- such as distinctions between declarative and procedural representation, propositional and analogical representation, and the nature of visual images -- are analyzed and found not to reflect fundamental disagreements.
...
...