Abstract
Many scientific publications and materials on artificial intelligence (AI) have been written in English; however, for many AI learners, English is their second language. Therefore, the difficulty (readability) of online self-teaching texts on AI for English-as-a-second-language (ESL) learners is essential for determining the language support ESL learners need to learn AI. However, only a few studies have addressed this issue. Therefore, we identified the difficulty level of English self-teaching texts for ESL AI learners. Because large-scale testing for ESL learners is impractical owing to the financial costs and time involved, we built two distinctive automatic readability assessors: one using sophisticated deep-learning-based natural language processing (NLP) technology, and another using classic NLP based on word frequency and applied linguistics. We conducted our evaluation using AI research papers and university-level online course texts. Interestingly, the distinctive automatic assessors, which were trained on different datasets, showed similar results. Intermediate-level ESL learners could read approximately 10% of online course texts. We also showed that they are significantly easier to read than AI research papers for ESL learners, demonstrating their usefulness in AI learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
“The AAAI Conference on Artificial Intelligence (AAAI)” papers in https://www.aaai.org/Conferences/conferences.php.
References
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of NAACL, Minneapolis, Minnesota, pp. 4171–4186, June 2019
Ehara, Y.: Building an English vocabulary knowledge dataset of Japanese English-as-a-second-language learners using crowdsourcing. In: Proceedings of LREC, May 2018
Ehara, Y.: Lurat: a lightweight unsupervised automatic readability assessment toolkit for second language learners. In: Proceeding of ICTAI, pp. 806–814. IEEE (2021)
Laufer, B., Ravenhorst-Kalovski, G.C.: Lexical threshold revisited: lexical text coverage, learners’ vocabulary size and reading comprehension. Read. Foreign Lang. 22(1), 15–30 (2010)
Nation, I.: How large a vocabulary is needed for reading and listening? Can. Mod. Lang. Rev. 63(1), 59–82 (2006)
Vajjala, S., Lučić, I.: OneStopEnglish corpus: a new corpus for automatic readability assessment and text simplification. In: Proceedings of BEA, pp. 297–304 (2018)
Acknowledgements
This work was supported by JST ACT-X Grant Number JPMJAX2006, Japan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Ehara, Y. (2022). Assessing Readability of Learning Materials on Artificial Intelligence in English for Second Language Learners. In: Rodrigo, M.M., Matsuda, N., Cristea, A.I., Dimitrova, V. (eds) Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium. AIED 2022. Lecture Notes in Computer Science, vol 13356. Springer, Cham. https://doi.org/10.1007/978-3-031-11647-6_96
Download citation
DOI: https://doi.org/10.1007/978-3-031-11647-6_96
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11646-9
Online ISBN: 978-3-031-11647-6
eBook Packages: Computer ScienceComputer Science (R0)