A parallel distributed processing model of visual word recognition and pronunciation is described. The model consists of sets of orthographic and phonologlc ~ units and an interlevel of hidden units. Weights on connections between units were modified during a training phase using the back-propa-gation learning algorithm. The model simulates many aspects of human performance, including (a) differences bet~n~.'n words in terms of processing difficulty, (b) pronunciation of novel items, (c) differences between readers in terms of word recognition skill, (d) transitions from beginning to skilled reading, and (e) differences in performance on lexieal decision and naming tasks. The model's behavior early in the learning phase corresponds to that of children acquiring word recognition skills. Training with a smaller number of hidden units produces output characteristic of many dys-lexic readers. Naming is simulated without pronunciation rules, and lexical decisions are simulated without accessing word-level representations. The performance of the model is largely determined by three factors: the nature of the input, a significant fragment of written English; the learning rule, which encodes the implicit structure of the orthography in the weights on connections; and the architecture of the system, which influences the scope of what can be learned. The recognition and pronunciation of words is one of the cen-

We develop a connectionist approach to processing in quasi-regular domains, as exemplified by English word reading. A consideration of the shortcomings of a previous implementation (Seidenberg & McClelland, 1989, Psych. Rev.) in reading nonwords leads to the development of orthographic and phonological representations that capture better the relevant structure among the written and spoken forms of words. In a number of simulation experiments, networks using the new representations learn to read both regular and exception words, including low-frequency exception words, and yet are still able to read pronounceable nonwords as well as skilled readers. A mathematical analysis of the effects of word frequency and spelling-sound consistency in a related but simpler system serves to clarify the close relationship of these factors in influencing naming latencies. These insights are verified in subsequent simulations, including an attractor network that reproduces the naming latency data directly in its time to settle on a response. Further analyses of the network's ability to reproduce data on impaired reading in surface dyslexia support a view of the reading system that incorporates a graded division-of-labor between semantic and phonological processes. Such a view is consistent with the more general Seidenberg and McClelland framework and has some similarities with---but also important differences from---the standard dual-route account.

Deep dyslexia is an acquired reading disorder marked by the occurrence of semantic errors (e.g., reading RIVER as "ocean"). In addition, patients exhibit a number of other symptoms, including visual and morphological effects in their errors, a part-of-speech effect, and an advantage for concrete over abstract words. Deep dyslexia poses a distinct challenge for cognitive neuropsychology because there is little understanding of why such a variety of symptoms should co-occur in virtually all known patients. Hinton and Shallice (1991) replicated the co-occurrence of visual and semantic errors by lesioning a recurrent connectionist network trained to map from orthography to semantics. While the success of their simulations is encouraging, there is little understanding of what underlying principles are responsible for them. In this paper we evaluate and, where possible, improve on the most important design decisions made by Hinton and Shallice, relating to the task, the network architecture, the training procedure, and the testing procedure. We identify four properties of networks that underly their ability to reproduce the deep dyslexic symptom-complex: distributed orthographic and semantic representations, gradient descent learning, attractors for word meanings, and greater richness of concrete vs. abstract semantics. The first three of these are general connectionist principles and the last is based on earlier theorizing. Taken together, the results demonstrate the usefulness of a connectionist approach to understanding deep dyslexia in particular, and the viability of connectionist neuropsychology in general.

Abstract not found

Many theorists assume that the cognitive system is composed of a collection of encapsulated processing components or modules, each dedicated to performing a particular cognitive function. On this view, selective impairments of cognitive tasks following brain damage, as evidenced by double dissociations, are naturally interpreted in terms of the loss of particular processing components. By contrast, the current investigation examines in detail a double dissociation between concrete and abstract word reading after damage to a connectionist network that pronounces words via meaning and yet has no separable components (Plaut & Shallice, 1993). The functional specialization in the network that gives rise to the double dissociation is not transparently related to the network's structure, as modular theories assume. Furthermore, a consideration of the distribution of effects across quantitatively equivalent individual lesions in the network raises specific concerns about the interpretation of...

this article, in conjunction with those developed previously (Plaut et al., 1996; Seidenberg & McClelland, 1989), illustrate how connectionist computational principles---distributed representation, structure-sensitive learning, and interactivity---can provide insight into central empirical phenomena in normal and impaired lexical processing. Moreover, they make it clear that distinctions in the function of the lexical system---as manifest in the behaviour of experimental subjects--- need not re#ect corresponding distinctions in the structure of the system. Thus, networks exhibit word-frequency effects and word/nonword discrimination without word representations, and spelling --sound consistency effects without separate mechanisms for regular and exception items. In this way, gaining insight into the structure and function of the cognitive system by observing its normal and impaired behaviour ---the central goal of cognitive psychology and neuropsycho logy---may depend critically on developing theories and explicit simulations in the context of a speci#c computational framework that relates structure to function

An interactive 2-step theory of lexical retrieval was applied to the picture-naming error patterns of aphasic and nonaphasic speakers. The theory uses spreading activation in a lexical network to accomplish the mapping between the conceptual representation of an object and the phonological form of the word naming the object. A model developed from the theory was parameterized to fit normal error patterns. It was then "lesioned " by globally altering its connection weight, decay rates, or both to provide fits to the error patterns of 21 fluent aphasic patients. These fits were then used to derive predictions about the influence of syntactic categories on patient errors, the effect of phonology on semantic errors, error patterns after recovery, and patient performance on a single-word repetition task. The predictions were confirmed. It is argued that simple quantitative alterations to a normal processing model can explain much of the variety among patient patterns in naming. Difficulty in word retrieval is the most pervasive symptom of language breakdown in aphasia. As with other symptoms of brain damage, word retrieval is subject to graceful degradation (Marr, 1982; Rumelhart & McClelland, 1986): Unsuccessful attempts at retrieval generally resemble the target, either in

This Special Issue on Connectionist Models of Human Language Processing provides an opportunity for an appraisal both of specific connectionist models and of the status and utility of connectionist models of language in general. This introduction provides the background for the papers in the Special Issue. The development of connectionist models of language is traced, from their intellectual origins, to the state of current research. Key themes that arise throughout different areas of connectionist psycholinguistics are highlighted, and recent developments in speech processing, morphology, sentence processing, language production, and reading are described. We argue that connectionist psycholinguistics has already had a significant impact on the psychology of language, and that connectionist models are likely to have an important influence on future research. Introduction Connectionist modeling of language processing has been highly controversial. Some have argued that language proce...

Connectionist modeling offers a useful computational framework for exploring the nature of normal and impaired cognitive processes. The current work extends the relevance of connectionist modeling in neuropsychology to address issues in cognitive rehabilitation: the degree and speed of recovery through retraining, the extent to which improvement on treated items generalizes to untreated items, and how treated items are selected to maximize this generalization. A network previously used to model impairments in mapping orthography to semantics is retrained after damage. The degree of relearning and generalization varies considerably for different lesion locations, and has interesting implications for understanding the nature and variability of recovery in patients. In a second simulation, retraining on words whose semantics are atypical of their category yields more generalization than retraining on more typical words, suggesting a counterintuitive strategy for selecting items in patient therapy to maximize recovery. In a final simulation, changes in the pattern of errors produced by the network over the course of recovery is used to constrain explanations of the nature of recovery of analogous brain-damaged patients. Taken together, the findings demonstrate that the nature of relearning in damaged connectionist networks can make important contributions to a theory of rehabilitation in patients.

xi 1 Introduction 1 1.1 Intuitions and Evidence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2 Previous Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.1 The Classical Dual Route Model . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.2 Seidenberg and McClelland 1989 . . . . . . . . . . . . . . . . . . . . . . 10 1.2.3 Plaut and Shallice 1993 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.2.4 Plaut et al. 1996: Naming . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.2.5 Bullinaria 1996 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 1.2.6 Plaut 1997: Lexical Decision . . . . . . . . . . . . . . . . . . . . . . . . . 15 1.2.7 Harm and Seidenberg 1998: Naming . . . . . . . . . . . . . . . . . . . . 16 1.3 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2 A New Computational Model 18 2.1 Principles . . . . . . . . . . . . . . . . . . . . . . . . ...