Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - A neuroconstructivist model of past tense development and processing
AU - Westermann, Gert
AU - Ruh, Nicolas
PY - 2012
Y1 - 2012
N2 - We present a neural network model of learning and processing the English past tense that is based on the notion that experience-dependent cortical development is a core aspect of cognitive development. During learning the model adds and removes units and connections to develop a task-specific final architecture. The model provides an integrated account of characteristic errors during learning the past tense, adult generalization to pseudoverbs, and dissociations between verbs observed after brain damage in aphasic patients. We put forward a theory of verb inflection in which a functional processing architecture develops through interactions between experience-dependent brain development and the structure of the environment, in this case, the statistical properties of verbs in the language. The outcome of this process is a structured processing system giving rise to graded dissociations between verbs that are easy and verbs that are hard to learn and process. In contrast to dual-mechanism accounts of inflection, we argue that describing dissociations as a dichotomy between regular and irregular verbs is a post hoc abstraction and is not linked to underlying processing mechanisms. We extend current single-mechanism accounts of inflection by highlighting the role of structural adaptation in development and in the formation of the adult processing system. In contrast to some single-mechanism accounts, we argue that the link between irregular inflection and verb semantics is not causal and that existing data can be explained on the basis of phonological representations alone. This work highlights the benefit of taking brain development seriously in theories of cognitive development. (PsycINFO Database Record (c) 2012 APA, all rights reserved).
AB - We present a neural network model of learning and processing the English past tense that is based on the notion that experience-dependent cortical development is a core aspect of cognitive development. During learning the model adds and removes units and connections to develop a task-specific final architecture. The model provides an integrated account of characteristic errors during learning the past tense, adult generalization to pseudoverbs, and dissociations between verbs observed after brain damage in aphasic patients. We put forward a theory of verb inflection in which a functional processing architecture develops through interactions between experience-dependent brain development and the structure of the environment, in this case, the statistical properties of verbs in the language. The outcome of this process is a structured processing system giving rise to graded dissociations between verbs that are easy and verbs that are hard to learn and process. In contrast to dual-mechanism accounts of inflection, we argue that describing dissociations as a dichotomy between regular and irregular verbs is a post hoc abstraction and is not linked to underlying processing mechanisms. We extend current single-mechanism accounts of inflection by highlighting the role of structural adaptation in development and in the formation of the adult processing system. In contrast to some single-mechanism accounts, we argue that the link between irregular inflection and verb semantics is not causal and that existing data can be explained on the basis of phonological representations alone. This work highlights the benefit of taking brain development seriously in theories of cognitive development. (PsycINFO Database Record (c) 2012 APA, all rights reserved).
UR - http://www.scopus.com/inward/record.url?scp=84867357100&partnerID=8YFLogxK
U2 - 10.1037/a0028258
DO - 10.1037/a0028258
M3 - Journal article
C2 - 22545787
VL - 119
SP - 649
EP - 667
JO - Psychological Review
JF - Psychological Review
SN - 0033-295X
IS - 3
ER -