Kuwait-University-Journal-of-Law-header
Search
Journal of Law

Previous Issues

Advance Search
Year : From To Vol
Issue Discipline:
Author

Volume :8 Issue : 32 1988      Add To Cart                                                                    Download

Computational Linguistics and Artificial Intelligence: Implications for Computer Assisted Language Learning

Auther : Ali Farghaly

The first generation of Computer Assisted language Learning (CALL) Programs was developed primarily by programmers and was pedagogically very poor. Second generation CALL software is characterized by the involvement of language teaching professionals in developing ESL software. It is proposed that third generation CALL software should have more reasoning power. The programs should be able to solve the problems that are set to students (Bonnet 1984).

In this paper we present a description of Artificial Intelligence and Computational Linguistics tools that could be used in CALL such as parsing, knowledge representation and expert systems. Both the capabilities and limitations of such tools are discussed and it is proposed that a model for intelligent CALL programs (MICALI) must be developed as a natural language processing system and should employ tools and techniques used in these disciplines. However; these tools are both modified to meet pedagogical requirements and supplemented by a host of other programs (pedagogical component) for error detection, analysis and feedback.

With these tools the third generation of CALL has the advantage over second generation software in that it is highly interactive and communicative. First, it does not store answers to the questions posed to students. Therefor no limitations are imposed on the type of questions in CALL. Creativity of software developers are used to the full. Second, It is bi-directional in the sense that it can either initiate a conversation with a student by asking him questions on a topic chosen by the student or respond to questions posed by students on a previously defined specific domain of knowledge. Although the new generation of CALL can be very powerful, it is realized that, with the present state of the art, it can only operate in limited parsing and domain - specific knowledge representation. 

Journal of Law
Journal of Law

You are Visitor No.

100174

Journal of Law
Journal of Law
Tell your friendsJournal of Law
Journal of Law
Journal of Law

Last Updated

Dec 08, 2019

Journal of Law
Journal of Law
Journal of Law

Please enter your email Here to receive our news

Journal of Law