Lancaster EPrints

Connectionist approaches to language learning

Westermann, Gert and Ruh, Nicolas and Plunkett, Kim (2009) Connectionist approaches to language learning. Linguistics, 47 (2). pp. 413-452. ISSN 1613-396X

Full text not available from this repository.

Abstract

In the past twenty years the connectionist approach to language development and learning has emerged as an alternative,e to traditional linguistic theories. This article introduces the connectionist paradigm by describing basic operating principles of neural network models as it;ell as different network architectures. The application of neural network models to explanations for linguistic problems is illustrated by reviewing a number of models for different aspects of language development, from speech sound acquisition to the development of syntax. Two main ben(fits of the connectionist approach are highlighted: implemented models offer a high degree of specificity, for a particular theory, and the explicit integration of a learning process into theory building allows for detailed investigation of the effect of he linguistic environment on a child. Issues regarding learnability or the need to assume innate and domain specific knowledge thus become an empirical question that can be answered by evaluating a model's performance.

Item Type: Article
Journal or Publication Title: Linguistics
Uncontrolled Keywords: ENGLISH PAST TENSE ; EARLY LEXICAL DEVELOPMENT ; GERMAN INFLECTION ; VERB MORPHOLOGY ; COGNITIVE-DEVELOPMENT ; SELF-ORGANIZATION ; SPEECH-PERCEPTION ; DYNAMIC-SYSTEMS ; NEURAL NETWORKS ; MODEL
Subjects:
Departments: Faculty of Science and Technology > Psychology
ID Code: 50888
Deposited By: ep_importer_pure
Deposited On: 08 Nov 2011 14:18
Refereed?: Yes
Published?: Published
Last Modified: 24 Oct 2013 10:27
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/50888

Actions (login required)

View Item