A Conversational Intelligent Tutoring System for Improving English Proficiency of Non-Native Speakers via Debriefing of Online Meeting Transcriptions

Juan Antonio Pérez-Ortiz, Miquel Esplà-Gomis, Víctor M. Sánchez-Cartagena, Felipe Sánchez-Martínez, Roman Chernysh, Gabriel Mora-Rodríguez, Lev Berezhnoy

Abstract:

This paper presents work-in-progress on developing a conversational tutoring system designed to enhance non-native English speakers’ language skills through post-meeting analysis of the transcriptions of video conferences in which they have participated. Following recent advances in chatbots and agents based on large language models (LLMs), our system leverages pre-trained LLMs within an
ecosystem that integrates different techniques, including in-context learning, external nonparametric memory retrieval, efficient parameter fine-tuning, grammatical error correction models, and error-preserving speech synthesis and recognition. While the system is still in development, a preliminary pilot evaluation of a prototype has been conducted with L2 English students.