In M.H. Christiansen & N. Chater (Eds.), Connectionist psycholinguistics (pp.19-75). Westport, CT: Ablex.

Connectionist Psycholinguistics in Perspective

Introduction

Connectionist approaches to language have been, and still are, highly controversial. Some have argued that natural language processing from phonology to semantics can be understood in connectionist terms; others have argued that no aspects of natural language can be captured by connectionist methods. And the controversy is particularly heated because of the revisionist claims of some connectionists:for many, connectionism is not just an additional method for studying language processing, but it offers an alternative to traditional theories, which describe language and language processing in symbolic terms. Indeed, Rumelhart and McClelland (1987:p. 196) suggest "that implicit knowledge of language may be stored among simple processing units organized into networks. While the behavior of such networks may be describable (at least approximately) as conforming to some system of rules, we suggest that an account of the fine structure of the phenomena of language and language acquisition can best be formulated in models that make reference to the characteristics of the underlying networks." We shall see that the degree to which connectionism supplants, rather than complements, existing approaches to language is itself a matter of debate. Finally, the controversy over connectionist approaches to language is an important test case for the validity of connectionist methods in other areas of psychology.

In this chapter, we aim to set the scene for the present volume on connectionist psycholinguistics, providing brief historical and theoretical background as well as an update on current research in the specific topic areas outlined below. In Background we describe the historical and intellectual roots of connectionism, then introduce the elements of modern connectionism, how it has been applied to natural language processing, and outline some of the theoretical claims that have been made for and against it. We then consider five central topics within connectionist psycholinguistics: Speech Processing, Morphology, Sentence Processing, Language Production, and Reading. We evaluate the research in each of these areas in terms of the three criteria for connectionist psycholinguistics discussed in Chapter 1 (this volume):data contact, task veridicality, and input representativeness. The five topics illustrate the range of connectionist research on language discussed in more depth in the following chapters in Part I of this volume. They also provide an opportunity to assess the strengths and weaknesses of connectionist methods across this range, setting the stage for the general debate concerning the validity of connectionist methods in Part II of this volume. Finally, in the Conclusions we sum up and consider the prospects for future connectionist research, and its relation to other approaches to the understanding of language processing and linguistic structure.


Click here to download a PDF version.

Home | People | Research | Links | Contact | Publications | Presentations