AI-Driven Inclusion: Exploring Automatic Text Simplification and Complexity Evaluation for Enhanced Educational Accessibility

Inclusive education is one of the 17 Sustainable Development Goals that aims to guarantee access and participation to all students considering their learning needs and competencies. Such a goal is particularly relevant in developing countries where socioeconomic conditions make it difficult to provide education, leading to a rate of illiterate adults higher than 99%, and millions of children aged 6–11 either do not attend school or drop out before completing primary education. Inclusive education is organized according to the learner’s needs helping to smooth out the knowledge gap among peers. Reading proficiency is one-factor influencing students’ engagement in learning activities. A low level can hamper content comprehension, thus acting negatively on students’ motivation. In the higher education sector, students’ reading proficiency is affected by different factors such as background and experiences, special educational needs, and general interests. Consequently, increasing the students’ engagement needs a personalized didactic plan that includes educational material according to the reading proficiency. Innovative Artificial Intelligence approaches to language complexity play a key role in fostering inclusive education. In particular, Automatic Text Simplification (ATS) and Automatic Text Complexity Evaluation (ATCE) represent effective solutions in this context. This paper aims to introduce both ATS and ATCE research fields, focusing on how the application of related systems might be useful in tackling the inclusion problem in the educational environment.