Intelligent Language Tutors: Theory Shaping Technology

Intelligent Language Tutors: Theory Shaping Technology

Intelligent Language Tutors: Theory Shaping Technology

Intelligent Language Tutors: Theory Shaping Technology


The techniques of natural language processing (NLP) have been widely applied in machine translation and automated message understanding, but have only recently been utilized in second language teaching. This book offers both an argument for and a critical examination of this new application, with an examination of how systems may be designed to exploit the power of NLP, accomodate its limitations, and minimize its risks. This volume marks the first collection of work in the U. S. and Canada that incorporates advanced human language technologies into language tutoring systems, covering languages as diverse as Arabic, Spanish, Japanese, and English.

The book is organized into sections that express the levels of analysis dealt with in learning and teaching a language and with the tasks of the student as writer, reader, conversant, and actor in the world. These sections bring together research by specialists in linguistics, artificial intelligence, psychology, instructional design, and language teaching. In addition to providing detailed descriptions of working systems, amply illustrated with screens from lesson and authoring interfaces, the contributors address a spectrum of common issues:

• What can current NLP technology contribute to computer-assisted language instruction and to research on language learning?

• How can this technology meet the demands of pedagogical theory for communicative language teaching in authentic contexts?

• How can designers constrain tutoring environments to ensure accurate analysis of learners' language?

• What can NLP-based systems teach us about language acquisition, about linguistic theory, and about theories of language pedagogy?

• What lessons have been learned in using these systems to date?

Discipline-specific issues are illuminated as well: the relative merits of the major syntactic frameworks for NLP-based language tutoring; the adaptation of theories like lexical conceptual structure to support semantic interpretation; the integration of input language with visual microworlds and dialogue games; the pragmatics of the tutoring discourse; the selection of instructional principles to guide system design; and the accomodation of design to individual differences and learner styles. A concluding section assesses this work from larger theoretical and practical perspectives -- experimental psychology and psycholinguistics, linguistics, language teaching, and second language acquisition research.


V. Melissa Holland
U.S. Army Research Institute

This book offers an argument for intelligent computer-assisted language learning (ICALL), an emerging discipline that seeks to apply advanced technologies, especially natural language processing (NLP), to the problems of language learning and research on learning. the contributors explain how they use nlp to enrich the capabilities of language tutors and learning environments. Where reactions from students are available, these are reported. the argument for icall is tempered throughout the book with lessons learned about the limitations of the technology and the complexities of applying it.

Nlp technology provides ways of programming the computer with enough information about language, in the form of rules and patterns, that it can analyze the structure of sentences that users put into it, catch or disregard errors, and in some cases appear to understand by carrying out requests or responding conversationally. This technology has evolved primarily through applications like machine translation (Nirenburg, 1993) and automated message extraction (ARPA, 1994). It has only rarely, and relatively recently, been applied to language learning. nlp gives language learners the ability to create original sentences in the language they are learning and enter them into the computer for feedback and response. This is as dramatic a departure from answering the multiple choice and fill-in-the-blank questions of conventional computerassisted instruction (CAI) as it is from observing other people's use of language in interactive video instruction.

The Neglect of icall

At this writing, we know of only one published book on icall, edited by Swartz and Yazdani (1992). Their book features European work, whereas this one focuses on U.S. and Canadian contributions. Why is the treatment so limited? Why, in general, do we hear so little about these efforts?

As a program of research, the projects that count as icall are scattered in place and time. There is not the critical mass to create a science, whose progress can be charted and whose efforts build on each other to make the cumulative improvements that come with replication and testing. More basically, unlike machine translation or automated message extraction, icall has no uniform impetus, no steady source of research funds, and no agreed-on methods for measuring success. Indeed, most systems are not finished enough to support evaluations.

As an application, icall suffers from the generally low priority assigned to for eign language education in this country. Where it is a priority, the politics and pragmatics of language education typically call for other kinds of learning tools, such as the lively interactive video and multimedia programs that have captured the public's eye (Fletcher, 1990; Furstenberg, 1992; Hart, 1994; Murray, this volume; Rubin, Ediger, Coffin, Van Handler . . .

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.