To simplify or not? Facilitating English <scp>L2</scp> users' comprehension and processing of open educational resources in English using text simplification

The occurrence of unknown words in texts significantly hinders reading comprehension. To improve accessibility for specific target populations, computational modelling has been applied to identify complex words in texts and substitute them for simpler alternatives. In this paper, we present an overview of computational approaches to lexical complexity prediction focusing on the work carried out on English data. We survey relevant approaches to this problem which include traditional machine learning classifiers (e.g. SVMs, logistic regression) and deep neural networks as well as a variety of features, such as those inspired by literature in psycholinguistics as well as word frequency, word length, and many others. Furthermore, we introduce readers to past competitions and available datasets created on this topic. Finally, we include brief sections on applications of lexical complexity prediction, such as readability and text simplification, together with related studies on languages other than English.

show abstract

“…A common approach among CALL is to simplify a text so as to make it more accessible for the L2 learner [108]. Morris, et al, 2013 [156].…”

Section: Improving Readabilitymentioning

confidence: 99%

Lexical Complexity Prediction: An Overview

2023

View full text Add to dashboard Cite

show abstract

“…Text Frontiers in Psychology frontiersin.org simplification, in natural language processing, aims at producing a simplified version of the original sentence to facilitate reading and understanding. Studies showed that the simplified text could benefit foreign language learners (Yano et al, 1994), leading to better text comprehension, particularly for people at lower English proficiency levels (Rets and Rogaten, 2021) and children with low reading fluency and weak cognitive skills (Javourey-Drevet et al, 2022).…”

Section: Text Simplificationmentioning

confidence: 99%

Reading bots: The implication of deep learning on guided reading

Huang

Dou²,

Zhang³

2023

Front. Psychol.

View full text Add to dashboard Cite

This study introduces the application of deep-learning technologies in automatically generating guidance for independent reading. 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. As a result, the novel design and implementation of a prototype system based on deep learning technologies are presented. 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. 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. 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.

show abstract

“…However, both tasks are rarely studied for question generation (Lyu et al, 2021). Simplification, on the other hand, has demonstrated its values in language learning and reading comprehension (Tweissi, 1998;Inui et al, 2003;Petersen and Ostendorf, 2007;Rets and Rogaten, 2021), and is often treated as a preprocessing step to convert complex sentences into simpler versions before creating questions (Majumder and Saha, 2015;Patra and Saha, 2019). State-of-the-art NLP models for these three tasks are all based on neural generation systems, which are known to suffer from errors and lack of controllability (Maynez et al, 2020).…”

Section: Nlp Tasks For Educationmentioning

confidence: 99%

Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs

Wang¹,

Fan²,

Houghton³

et al. 2022

Preprint

View full text Add to dashboard Cite

NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning. Yet, QG systems have not been widely adopted in classrooms to date. In this work, we aim to pinpoint key impediments and investigate how to improve the usability of automatic QG techniques for educational purposes by understanding how instructors construct questions and identifying touch points to enhance the underlying NLP models. We perform an in-depth need finding study with 11 instructors across 7 different universities, and summarize their thought processes and needs when creating questions. While instructors show great interests in using NLP systems to support question design, none of them has used such tools in practice. They resort to multiple sources of information, ranging from domain knowledge to students' misconceptions, all of which missing from today's QG systems. We argue that building effective human-NLP collaborative QG systems that emphasize instructor control and explainability is imperative for real-world adoption. We call for QG systems to provide processoriented support, use modular design, and handle diverse sources of input.

show abstract

To simplify or not? Facilitating English L2 users' comprehension and processing of open educational resources in English using text simplification

Cited by 24 publications

References 40 publications

Lexical Complexity Prediction: An Overview

Lexical Complexity Prediction: An Overview

Reading bots: The implication of deep learning on guided reading

Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs

Contact Info

Product

Resources

About