TUTORING: Instruction-Grounded Conversational Agent for Language Learners

Authors

  • Hyungjoo Chae Yonsei University Tutoring, Market Designers Inc.
  • Minjin Kim Yonsei University
  • Chaehyeong Kim Yonsei University
  • Wonseok Jeong Market Designers Inc.
  • Hyejoong Kim Market Designers Inc.
  • Junmyung Lee Market Designers Inc.
  • Jinyoung Yeo Yonsei University Tutoring, Market Designers Inc.

DOI:

https://doi.org/10.1609/aaai.v37i13.27063

Keywords:

SNLP: Conversational AI/Dialogue Systems, APP: Education, HAI: Language Acquisition

Abstract

In this paper, we propose Tutoring bot, a generative chatbot trained on a large scale of tutor-student conversations for English-language learning. To mimic a human tutor's behavior in language education, the tutor bot leverages diverse educational instructions and grounds to each instruction as additional input context for the tutor response generation. As a single instruction generally involves multiple dialogue turns to give the student sufficient speaking practice, the tutor bot is required to monitor and capture when the current instruction should be kept or switched to the next instruction. For that, the tutor bot is learned to not only generate responses but also infer its teaching action and progress on the current conversation simultaneously by a multi-task learning scheme. Our Tutoring bot is deployed under a non-commercial use license at https://tutoringai.com.

Downloads

Published

2023-09-06

How to Cite

Chae, H., Kim, M., Kim, C., Jeong, W., Kim, H., Lee, J., & Yeo, J. (2023). TUTORING: Instruction-Grounded Conversational Agent for Language Learners. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16413-16415. https://doi.org/10.1609/aaai.v37i13.27063