[12] Promoting Learner–Computer Interaction with Extractive Question- Answer Technologies

Back to Exploring AI in Applied Linguistics

Promoting Learner–Computer Interaction with Extractive Question- Answer Technologies

This chapter is part of: Chapelle, C. A., Beckett, G. H., & Ranalli, J. (Eds.). (2024). Exploring artificial intelligence in applied linguistics. Iowa State University Digital Press. https://doi.org/10.31274/isudp.2024.154.

Download Chapter

Description
Integrating AI-based technologies into virtual environments (VEs) amplifies opportunities for independent learners to generate L2 output (Zou et al., 2023). This paper outlines the integration process of Extractive Question Answering Transformers (EQATs) into VE design, aimed at enabling autonomous learners to engage in meaningful dialogue and negotiate for meaning with interactive dialogue systems. Additionally, a comprehensive client-side demonstration illustrating this integration is provided, involving the incorporation of two AI models: the Universal Sentence Encoder (USE) and Adaptive Question and Answer (AQ&A). These models are utilized to respond to learner queries based on domain-specific (i.e., task-specific) data. Finally, the paper discusses the benefits of developing such educational applications through collaborative efforts among developers, materials designers, and instructors.

Description

Integrating AI-based technologies into virtual environments (VEs) amplifies opportunities for independent learners to generate L2 output (Zou et al., 2023). This paper outlines the integration process of Extractive Question Answering Transformers (EQATs) into VE design, aimed at enabling autonomous learners to engage in meaningful dialogue and negotiate for meaning with interactive dialogue systems. Additionally, a comprehensive client-side demonstration illustrating this integration is provided, involving the incorporation of two AI models: the Universal Sentence Encoder (USE) and Adaptive Question and Answer (AQ&A). These models are utilized to respond to learner queries based on domain-specific (i.e., task-specific) data. Finally, the paper discusses the benefits of developing such educational applications through collaborative efforts among developers, materials designers, and instructors.

Details

Published	Published By	Pages	DOI
July 31, 2024	Iowa State University Digital Press	15	10.31274/isudp.2024.154.12
License Information
©2024 The authors. Published under a CC BY license.
Citation
Collentine, J. (2024). Promoting learner-computer interaction with extractive question-answer technologies. In C. A. Chapelle, G. H. Beckett, & J. Ranalli (Eds.), Exploring artificial intelligence in applied linguistics (pp. 202–216). Iowa State University Digital Press. https://doi.org/10.31274/isudp.2024.154.12.