Incorporating Word-level Phonemic Decoding into Readability Assessment

Christine Pinney, Casey Kennington, Maria Soledad Pera, Katherine Landau Wright, Jerry Alan Fails. 2024. “Incorporating Word-level Phonemic Decoding into Readability Assessment”. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). ACL, pp. 8998–9009. DOI:2024.lrec-main.788

Abstract

We discuss the foundation of a collaborative effort to explore AI’s role in supporting (teachers and) children in their learning experiences. We integrate principles of educational psychology, AI, and HCI, and align with best practices in education while undertaking a human-centered focus on design and development that puts the student at the centre and keeps the expert-in-the-loop. Initially, we study assessment items—questions or tasks tied to a learning target. These items vary in complexity, serve as indicators of students’ grasp of specific concepts and spotlight areas where support may be needed. This preliminary analysis will help us outline a framework to guide the design and evaluation of AI technology for K-12 education. Such a framework would ensure that assessment item generation technology goes beyond the current one-dimensional approach by incorporating multifaceted, adaptable perspectives that consider the variegated landscape of learners’ needs, subject matter complexities, and pedagogical goals.

Updated: