Newswise – For students learning a second or foreign language, the text is often simplified to ensure they can understand it well enough to get the main message. Usually complicated texts in a foreign language are simplified manually by teachers or material designers. However, with the advent of artificial intelligence (AI) based software, automatic text simplification has become a reality. One such tool is Automatic Text Simplification (ATS) software, which simplifies texts in second and foreign languages for L2 learners. There is currently limited data on the effectiveness of any ATS software in an educational setting.
To address this, Professor Dennis Murphy Odo of Pusan National University’s Department of English Education conducted a study published in Applied Linguisticsto assess how L2 learners understand English language text simplified by an ATS tool. To do this, he recruited 61 Korean native speakers who have been learning English for 10 years and whose reading skills range from low to high.
These L2 learners were divided into low and high L2 reading ability groups and asked to read either authentic English text obtained from the Scientific American website or an automatically simplified version of the same text using an ATS tool, Yet Another Text Simplifier. (YATS). The L2 learners in both groups then completed a free recall test and a multiple-choice (MC) comprehension test, which tested their ability to recall and understand the text.
The main finding derived from an analysis of the results of the free recall test was that L2 learners with higher reading proficiency automatically found simplified text easier to understand than L2 learners with lower reading proficiency.
Discussing this finding, Prof. Odo notes: “Although automated online text simplification tools can prove extremely useful in making authentic materials more understandable for L2 learners beyond a certain level of reading proficiency in a foreign language, they may not be able to do the same for learners with lower reading proficiency.”
Therefore, ATS software can help high-literacy L2 students understand complicated texts and assist teachers in simplifying difficult texts for their students.
However, there is a need to further develop ATS tools to make texts sufficiently understandable for L2 learners with low reading skills. “On the plus side, software developers will continue to develop AI-powered tools that make challenging text increasingly understandable for foreign language learners with different reading levels,” says Prof. Odo in conclusion.
About Pusan National University
Founded in 1946, Pusan National University in Busan, South Korea is now the No. 1 national university of South Korea in terms of research and educational excellence. The multi-campus university also has other smaller campuses in Yangsan, Miryang and Ami. The university prides itself on the principles of truth, liberty and service and has approximately 30,000 students, 1200 professors and 750 faculty members. The university consists of 14 colleges (schools) and one independent department with a total of 103 departments.
About the author
Professor Dennis Murphy Odo received his Ph.D. in Language and Literacy Education and has served as an in-service teacher trainer for TESOL methods in public schools for the Korean Ministry of Education. He has also served as an assistant professor of reading education at Georgia State University, where he taught first and second language reading courses. He is currently a professor in the Department of English Education at Pusan National University, where he teaches courses on second language acquisition and teaching methods for literacy. His main research interests include learner autonomy, technology, second language competency teaching and teacher development.
ORCID ID: 0000-0002-5438-0446