Large language models (LLMs), such as Codex, hold great promise in enhancing programming education by automatically generating feedback for students. We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key scenario in introductory programming. More concretely, given a student's buggy program, our goal is…

In recent years, advances in artificial intelligence (AI) have led to significantly improved, or in some cases, completely new digital tools for writing. Systems for writing assessment and assistance based on automated writing evaluation (AWE) have been available for some time. That is the case for machine translation as well. More recent are…

In this article, the authors examine different ways of using the Internet to receive feedback, and discuss advantages of language learners' use of the Internet to improve their own writing. In effect, the article elaborates on how Internet-mediated corrective feedback (IMCF) can be used as an efficient tool by language learners to become competent…

Previous studies on self-correction using corpora involve monolingual concordances and intervention from instructors such as marking of errors, the use of modified concordances, and other simplifications of the task. Can L2 learners independently refine their previous outputs by simply using a parallel concordancer without any hints about their…

When speakers detect a problem in what they are saying, they must decide whether or not to interrupt themselves and repair the problem, and if so, when. Speakers will maximize accuracy if they interrupt themselves as soon as they detect a problem, but they will maximize fluency if they go on speaking until they are ready to produce the repair.…