Home > Research > Publications & Outputs > Connectionist approaches to language learning

Research

Links

Text available via DOI:

Keywords

View graph of relations

Connectionist approaches to language learning

Research output: Contribution to Journal/Magazine › Literature review › peer-review

Published

Standard

Connectionist approaches to language learning. / Westermann, Gert; Ruh, Nicolas; Plunkett, Kim.
In: Linguistics, Vol. 47, No. 2, 03.2009, p. 413-452.

Research output: Contribution to Journal/Magazine › Literature review › peer-review

Harvard

Westermann, G, Ruh, N & Plunkett, K 2009, 'Connectionist approaches to language learning', Linguistics, vol. 47, no. 2, pp. 413-452. https://doi.org/10.1515/LING.2009.015

APA

Westermann, G., Ruh, N., & Plunkett, K. (2009). Connectionist approaches to language learning. Linguistics, 47(2), 413-452. https://doi.org/10.1515/LING.2009.015

Vancouver

Westermann G, Ruh N, Plunkett K. Connectionist approaches to language learning. Linguistics. 2009 Mar;47(2):413-452. doi: 10.1515/LING.2009.015

Author

Westermann, Gert ; Ruh, Nicolas ; Plunkett, Kim. / Connectionist approaches to language learning. In: Linguistics. 2009 ; Vol. 47, No. 2. pp. 413-452.

Bibtex

@article{6bd823aba0e24dc588ab79c679b90a5a,
title = "Connectionist approaches to language learning",
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.",
keywords = "ENGLISH PAST TENSE, EARLY LEXICAL DEVELOPMENT, GERMAN INFLECTION, VERB MORPHOLOGY, COGNITIVE-DEVELOPMENT, SELF-ORGANIZATION, SPEECH-PERCEPTION, DYNAMIC-SYSTEMS, NEURAL NETWORKS, MODEL",
author = "Gert Westermann and Nicolas Ruh and Kim Plunkett",
year = "2009",
month = mar,
doi = "10.1515/LING.2009.015",
language = "English",
volume = "47",
pages = "413--452",
journal = "Linguistics",
issn = "1613-396X",
publisher = "Walter de Gruyter GmbH & Co. KG",
number = "2",

}

RIS

TY - JOUR

T1 - Connectionist approaches to language learning

AU - Westermann, Gert

AU - Ruh, Nicolas

AU - Plunkett, Kim

PY - 2009/3

Y1 - 2009/3

N2 - 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.

AB - 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.

KW - ENGLISH PAST TENSE

KW - EARLY LEXICAL DEVELOPMENT

KW - GERMAN INFLECTION

KW - VERB MORPHOLOGY

KW - COGNITIVE-DEVELOPMENT

KW - SELF-ORGANIZATION

KW - SPEECH-PERCEPTION

KW - DYNAMIC-SYSTEMS

KW - NEURAL NETWORKS

KW - MODEL

U2 - 10.1515/LING.2009.015

DO - 10.1515/LING.2009.015

M3 - Literature review

VL - 47

SP - 413

EP - 452

JO - Linguistics

JF - Linguistics

SN - 1613-396X

IS - 2

ER -