Intelligent Corrective Feedback for Communicative Computer-Assisted Language Learning

Abstract

Although there have been enormous investments into English education all around the world, not many differences have been made to change the English instruction style. Considering the shortcomings for the current teaching-learning methodology, we have been investigating Dialog-Based Computer-Assisted Language Learning (DB-CALL) systems. This thesis contains a set of our approaches to DB-CALL including theories, technologies, systems, and field studies. On top of the state-of-the-art technologies of spoken dialog system, a variety of adaptations have been applied to overcome some problems caused by numerous errors and variations naturally produced by non-native speakers so that learners can engage in free conversations. While free conversation is invaluable to the acquisition process, it is not sufficient for learners to fully develop their second language proficiency. Corrective feedback to learners’ grammatical errors is necessary for improving accuracy in their interlanguage. The main contribution of this thesis lies in the research on intelligent corrective feedback that handles learners’ errors and helps learners to use more appropriate words and expressions. Many studies on detecting grammatical errors and generating corrective feedback have been done in written mode, but there has been a dearth of research in oral mode. This thesis proposes an effective strategy of corrective feedback in oral communication based on second language acquisition theory and practice, and presents efficient methods that enable the strategy.Integrating these efforts resulted in intelligent educational robots and virtual 3D language learning games. To verify the educational effects of our approaches on students’ communicative abilities, we have conducted a field study at an elementary school in Korea. The results showed that our DB-CALL approaches can be enjoyable and fruitful activities for students.