arise automatically as a result of the recursive structure of the task and the continuous nature of the SRN's state space. Elman also introduces a new graphical technique for study ing network behavior based on principal components analysis. He shows that sentences with multiple levels of embedding produce state space trajectories with an intriguing self similar structure. The development and shape of a recurrent network's state space is the subject of Pollack's paper, the most provocative in this collection. Pollack looks more closely at a connectionist network as a continuous dynamical system. He describes a new type of machine learning phenomenon: induction by phase transition. He then shows that under certain conditions, the state space created by these machines can have a fractal or chaotic structure, with a potentially infinite number of states. This is graphically illustrated using a higher-order recurrent network trained to recognize various regular languages over binary strings. Finally, Pollack suggests that it might be possible to exploit the fractal dynamics of these systems to achieve a generative capacity beyond that of finite-state machines.

This volume, in its 25 definitive chapters on normal and nonnormal language development, represents the authoritative and up-to-date complete sourcebook on child language development. All aspects of child language development are addressed, including phonetics, phonology, grammar, and lexical development. Connectionism and government-binding theory, as applied to language development, are fully represented. The relevance of input, cognition, and social factors to language development is explored. Chapters on methodology, particularly using computer databases, are provided for both normal and nonnormal acquisition.

The latest title in the Cognitive Science and Second Language Acquisition Series presents a comprehensive review of connectionist research in second language acquisition (SLA). Second language researchers and the cognitive science community will find accessible discussions of the relevance of connectionist research to SLA. This important volume is key reading for any student or researcher interested in how second language acquisition can be better understood from a connectionist perspective.

This book explores the contributions that cognitive linguistics and psychology, including neuropsychology, have made to the understanding of the way that second languages are processed and learnt. It examines areas of phonology, word recognition and semantics, examining 'bottom-up' decoding processes as compared with 'top-down' processes as they affect memory. It also discusses second language learning from the acquisition/learning and nativist/connectionist perspectives. These ideas are then related to the methods that are used to teach second languages, primarily English, in formal classroom situations. This examination involves both 'mainstream' communicative approaches, and more traditional methods widely used to teach EFL throughout the world. The book is intended to act both as a textbook for students who are studying second language teaching and as an exploration of issues for the interested teacher who would like to further extend their understanding of the cognitive processes underlying their teaching.Mick Randall is currently Senior Lecturer in TESOL and Head of the Institute of Education at the British University in Dubai. He has taught courses in second language learning and teaching, applied linguistics and psychology in a number of different contexts. He has a special interest in the cognitive processing of language and in the psycholinguistics of word recognition, spelling and reading.

Setting forth the state of the art, leading researchers present a survey on the fast-developing field of Connectionist Psycholinguistics: using connectionist or neural networks, which are inspired by brain architecture, to model empirical data on human language processing. Connectionist psycholinguistics has already had a substantial impact on the study of a wide range of aspects of language processing, ranging from inflectional morphology, to word recognition, to parsing and language production. Christiansen and Chater begin with an extended tutorial overview of Connectionist Psycholinguistics which is followed by the latest research by leading figures in each area of research. The book also focuses on the implications and prospects for connectionist models of language, not just for psycholinguistics, but also for computational and linguistic perspectives on natural language. The interdisciplinary approach will be relevant for, and accessible to psychologists, cognitive scientists, linguists, philosophers, and researchers in artificial intelligence.

Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state of the art continuous speech recognition systems based on hidden Markov models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e. HMM emission probability estimation and feature extraction. The book describes a successful five-year international collaboration between the authors. The lessons learned form a case study that demonstrates how hybrid systems can be developed to combine neural networks with more traditional statistical approaches. The book illustrates both the advantages and limitations of neural networks in the framework of a statistical systems. Using standard databases and comparison with some conventional approaches, it is shown that MLP probability estimation can improve recognition performance. Other approaches are discussed, though there is no such unequivocal experimental result for these methods. Connectionist Speech Recognition is of use to anyone intending to use neural networks for speech recognition or within the framework provided by an existing successful statistical approach. This includes research and development groups working in the field of speech recognition, both with standard and neural network approaches, as well as other pattern recognition and/or neural network researchers. The book is also suitable as a text for advanced courses on neural networks or speech processing.

Second language acquisition (SLA) is a field of inquiry that has increased in importance since the 1960s. Currently, researchers adopt multiple perspectives in the analysis of learner language, all of them providing different but complementary answers to the understanding of oral and written data produced by young and older learners in different settings. The main goal of this volume is to provide the reader with updated reviews of the major contemporary approaches to SLA, the research carried out within them and, wherever appropriate, the implications and/or applications for theory, research and pedagogy that might derive from the available empirical evidence. The book is intended for SLA researchers as well as for graduate (MA, Ph.D.) students in SLA research, applied linguistics and linguistics, as the different chapters will be a guide in their research within the approaches presented. The volume will also be of interest to professionals from other fields interested in the SLA process and the different explanations that have been put forward to account for it.

Connectionist modelling and neural network applications had become a major sub-field of cognitive science by the mid-1990s. In this ground-breaking book, originally published in 1995, leading connectionists shed light on current approaches to memory and language modelling at the time. The book is divided into four sections: Memory; Reading; Computation and statistics; Speech and audition. Each section is introduced and set in context by the editors, allowing a wide range of language and memory issues to be addressed in one volume. This authoritative advanced level book will still be of interest for all engaged in connectionist research and the related areas of cognitive science concerned with language and memory.

What is language and how can we investigate its acquisition by children or adults? What perspectives exist from which to view acquisition? What internal constraints and external factors shape acquisition? What are the properties of interlanguage systems? This comprehensive 31-chapter handbook is an authoritative survey of second language acquisition (SLA). Its multi-perspective synopsis on recent developments in SLA research provides significant contributions by established experts and widely recognized younger talent. It covers cutting edge and emerging areas of enquiry not treated elsewhere in a single handbook, including third language acquisition, electronic communication, incomplete first language acquisition, alphabetic literacy and SLA, affect and the brain, discourse and identity. Written to be accessible to newcomers as well as experienced scholars of SLA, the Handbook is organised into six thematic sections, each with an editor-written introduction.

A cutting-edge reference source for the interdisciplinary field of computational cognitive modeling.