In addition, it can also assist the instructor to prepare the reading course materials with automatically generated questions, image and audio resources retrieved from knowledge graphs, and automatic grading of the essays submitted by readers. It guides the readers through reading activities in reading comprehension, including guiding questions, vocabulary building, analysis of complex and long sentences, multiple-choice question quizzes, and writing tasks. The reading bot can act as an instructor for readers with reading difficulties or assist them in preparing for a language test. In this study, we propose the concept of reading bots, which pioneers the application of the recent advances in deep learning-based natural language processing in the instructions of reading comprehension. However, despite the progress in natural language processing and heated waves in the commercialization of progress in chatbots, commodity recommendations, and other fields, the application of this progress for reading comprehension tutoring is still in its infancy. To solve the problem of increasing customer interactions, using deep-learning technologies, more and more chatbots are being deployed to imitate human communication and serve customers in the service industry. In the era where the “digital twin” in the metaverse gradually emerges as the substitution of the real world for humans and the advances in artificial intelligence, digital text is growing at an unprecedented pace, which brings about huge challenges for instructors. With the growing demand for personalized tutoring, the traditional computer technology or the ITS systems that heavily rely on manually compiled reading materials, supporting quizzes, and pictures are not sufficiently flexible and expandable to cope with the massive online materials. Artificial intelligence, including Bayesian networks and fuzzy logic, was used to adaptively support students in learning environments, which had shown positive results (Eryilmaz and Adabashi, 2020). These ITS systems assisted readers by acting as coaches (Hauptmann et al., 1994), reading companions (Madnani et al., 2019), or using augmented reality (Voogt and McKenney, 2007) to build interactive digital environments. Computer technology is a widely used vehicle to promote literacy of students in reading, as evidenced by a large number of studies that focused on the effects of intelligent tutoring system (ITS) in the age groups of children in grades 1–3 (Hauptmann et al., 1994), kindergarten (Voogt and McKenney, 2007), K-12 (from kindergarten to 12th grade) students (Proudfoot, 2016 Xu et al., 2019 Pahamzah et al., 2022), and adults (Ramachandran and Stottler, 2000). To maximize the effects of reading comprehension, instructors have developed a lot of strategies and tools, including computer technology. Reading comprehension is one of the primary ways for a human to acquire knowledge, and the cultivation of reading skills in students by instructors to facilitate the distillation of knowledge remains one of the central tasks in literary education. Based on the experiment results and the reported performance of the deep learning models on reading-related tasks, the study reveals the challenges and limitations of deep learning technologies, such as inadequate performance, domain transfer issues, and low explain ability, for future improvement. Experiments on word sense disambiguation, named entity recognition and question generation with real-world materials in the prototype system show that the selected deep learning models on these tasks obtain favorable results, but there are still errors to be overcome before their direct usage in real-world applications. This system includes connections to prior knowledge with knowledge graphs and summary-based question generation, the breakdown of complex sentences with text simplification, and the auto-grading of readers' writing regarding their comprehension of the reading materials. As a result, the novel design and implementation of a prototype system based on deep learning technologies are presented. The study explores and demonstrates how to incorporate the latest advances in deep-learning-based natural language processing technologies in the three reading stages, namely, the pre-reading stage, the while-reading stage, and the post-reading stage. This study introduces the application of deep-learning technologies in automatically generating guidance for independent reading.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |