Originally published in 1992, when connectionist natural language processing (CNLP) was a new and burgeoning research area, this book represented a timely assessment of the state of the art in the field. It includes contributions from some of the best known researchers in CNLP and covers a wide range of topics. The book comprises four main sections dealing with connectionist approaches to semantics, syntax, the debate on representational adequacy, and connectionist models of psycholinguistic processes. The semantics and syntax sections deal with a variety of approaches to issues in these traditional linguistic domains, covering the spectrum from pure connectionist approaches to hybrid models employing a mixture of connectionist and classical AI techniques. The debate on the fundamental suitability of connectionist architectures for dealing with natural language processing is the focus of the section on representational adequacy. The chapters in this section represent a range of positions on the issue, from the view that connectionist models are intrinsically unsuitable for all but the associationistic aspects of natural language, to the other extreme which holds that the classical conception of representation can be dispensed with altogether. The final section of the book focuses on the application of connectionist models to the study of psycholinguistic processes. This section is perhaps the most varied, covering topics from speech perception and speech production, to attentional deficits in reading. An introduction is provided at the beginning of each section which highlights the main issues relating to the section topic and puts the constituent chapters into a wider context.

Risto Miikkulainen draws on recent connectionist work in language comprehension tocreate a model that can understand natural language. Using the DISCERN system as an example, hedescribes a general approach to building high-level cognitive models from distributed neuralnetworks and shows how the special properties of such networks are useful in modeling humanperformance. In this approach connectionist networks are not only plausible models of isolatedcognitive phenomena, but also sufficient constituents for complete artificial intelligencesystems.Distributed neural networks have been very successful in modeling isolated cognitivephenomena, but complex high-level behavior has been tractable only with symbolic artificialintelligence techniques. Aiming to bridge this gap, Miikkulainen describes DISCERN, a completenatural language processing system implemented entirely at the subsymbolic level. In DISCERN,distributed neural network models of parsing, generating, reasoning, lexical processing, andepisodic memory are integrated into a single system that learns to read, paraphrase, and answerquestions about stereotypical narratives.Miikkulainen's work, which includes a comprehensive surveyof the connectionist literature related to natural language processing, will prove especiallyvaluable to researchers interested in practical techniques for high-level representation,inferencing, memory modeling, and modular connectionist architectures.Risto Miikkulainen is anAssistant Professor in the Department of Computer Sciences at The University of Texas atAustin.

This book is based on the workshop on New Approaches to Learning for Natural Language Processing, held in conjunction with the International Joint Conference on Artificial Intelligence, IJCAI'95, in Montreal, Canada in August 1995. Most of the 32 papers included in the book are revised selected workshop presentations; some papers were individually solicited from members of the workshop program committee to give the book an overall completeness. Also included, and written with the novice reader in mind, is a comprehensive introductory survey by the volume editors. The volume presents the state of the art in the most promising current approaches to learning for NLP and is thus compulsory reading for researchers in the field or for anyone applying the new techniques to challenging real-world NLP problems.

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.

Connection science is a new information-processing paradigm which attempts to imitate the architecture and process of the brain, and brings together researchers from disciplines as diverse as computer science, physics, psychology, philosophy, linguistics, biology, engineering, neuroscience and AI. Work in Connectionist Natural Language Processing (CNLP) is now expanding rapidly, yet much of the work is still only available in journals, some of them quite obscure. To make this research more accessible this book brings together an important and comprehensive set of articles from the journal CONNECTION SCIENCE which represent the state of the art in Connectionist natural language processing; from speech recognition to discourse comprehension. While it is quintessentially Connectionist, it also deals with hybrid systems, and will be of interest to both theoreticians as well as computer modellers. Range of topics covered: Connectionism and Cognitive Linguistics Motion, Chomsky's Government-binding Theory Syntactic Transformations on Distributed Representations Syntactic Neural Networks A Hybrid Symbolic/Connectionist Model for Understanding of Nouns Connectionism and Determinism in a Syntactic Parser Context Free Grammar Recognition Script Recognition with Hierarchical Feature Maps Attention Mechanisms in Language Script-Based Story Processing A Connectionist Account of Similarity in Vowel Harmony Learning Distributed Representations Connectionist Language Users Representation and Recognition of Temporal Patterns A Hybrid Model of Script Generation Networks that Learn about Phonological Features Pronunciation in Text-to-Speech Systems

Neural networks are a family of powerful machine learning models and this book focuses on their application to natural language data. The first half of the book (Parts I and II) covers the basics of supervised machine learning and feed-forward neural networks, the basics of working with machine learning over language data, and the use of vector-based rather than symbolic representations for words. It also covers the computation-graph abstraction, which allows to easily define and train arbitrary neural networks, and is the basis behind the design of contemporary neural network software libraries. The second part of the book (Parts III and IV) introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural networks, conditioned-generation models, and attention-based models. These architectures and techniques are the driving force behind state-of-the-art algorithms for machine translation, syntactic parsing, and many other applications. Finally, we also discuss tree-shaped networks, structured prediction, and the prospects of multi-task learning.

Studies in Computational Linguistics presents authoritative texts from an international team of leading computational linguists. The books range from the senior undergraduate textbook to the research level monograph and provide a showcase for a broad range of recent developments in the field. The series should be interesting reading for researchers and students alike involved at this interface of linguistics and computing.

This book is a collection of chapters describing work carried out as part of a large project at BT Laboratories to study the application of connectionist methods to problems in vision, speech and natural language processing. Also, since the theoretical formulation and the hardware realization of neural networks are significant tasks in themselves, these problems too were addressed. The book, therefore, is divided into five Parts, reporting results in vision, speech, natural language, hardware implementation and network architectures. The three editors of this book have, at one time or another, been involved in planning and running the connectionist project. From the outset, we were concerned to involve the academic community as widely as possible, and consequently, in its first year, over thirty university research groups were funded for small scale studies on the various topics. Co-ordinating such a widely spread project was no small task, and in order to concentrate minds and resources, sets of test problems were devised which were typical of the application areas and were difficult enough to be worthy of study. These are described in the text, and constitute one of the successes of the project.

Studies in Computational Linguistics presents authoritative texts from an international team of leading computational linguists. The books range from the senior undergraduate textbook to the research level monograph and provide a showcase for a broad range of recent developments in the field. The series should be interesting reading for researchers and students alike involved at this interface of linguistics and computing.