Automatic prediction of vocabulary knowledge for learners of Chinese as a foreign language

Lee, John; Yeung, Chak Yan

doi:10.1109/icnlsp.2018.8374392

Cited by 6 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only through understanding both what works and what does not can we form a holistic understanding of the topic. [7, 22, 46, 47, 62, 63, 71-73, 83, 87, 89, 94, 104, 107, 147, 149, 166, 172, 173, 177, 184, 186, 206, 208, 215, 218, 220, 231, 232, 244, 279, 296, 299, 315, 319, 327, 329, 337, 341, 358, 359, 373, 374, 407, 411, 424] Exam / Post-test Grade or Score [9,10,21,24,33,35,52,59,67,68,77,80,81,85,90,96,109,114,116,127,136,152,162,163,169,193,195,199,202,205,214,217,224,233,238,241,270,274,275,277,284,287,301,302,309,314,…”

Section: Calls To the Communitymentioning

confidence: 99%

Predicting academic performance: a systematic literature review

Hellas

Ihantola

Petersen

et al. 2018

Proceedings Companion of the 23rd Annual ACM Conference on Innovation and Technology in Computer Science Education

207

171

View full text Add to dashboard Cite

The ability to predict student performance in a course or program creates opportunities to improve educational outcomes. With effective performance prediction approaches, instructors can allocate resources and instruction more accurately. Research in this area seeks to identify features that can be used to make predictions, to identify algorithms that can improve predictions, and to quantify aspects of student performance. Moreover, research in predicting student performance seeks to determine interrelated features and to identify the underlying reasons why certain features work better than others. This working group report presents a systematic literature review of work in the area of predicting student performance. Our analysis shows a clearly increasing amount of research in this area, as well as an increasing variety of techniques used. At the same time, the review uncovered a number of issues with research quality that drives a need for the community to provide more detailed reporting of methods and results and to increase efforts to validate and replicate work.

show abstract

Section: Calls To the Communitymentioning

confidence: 99%

Predicting academic performance: a systematic literature review

Hellas

Ihantola

Petersen

et al. 2018

Proceedings Companion of the 23rd Annual ACM Conference on Innovation and Technology in Computer Science Education

207

171

View full text Add to dashboard Cite

show abstract

“…If, however, the word was assigned a complexity value of 4 or 5, then that word was labeled as being either challenging or non-complex respectively. Their SVM classifier was trained on a number of features parallel to Lee and Yeung [76]. These being, the target word's ranking in a Chinese proficiency test 14 , word length, word frequency in the Chinese Wikipedia Corpus [76] and the Jinan Corpus of Learner Chinese (JCLC) [140], along with Chinese character frequency in the JCLC.…”

Section: 21mentioning

confidence: 99%

“…Their SVM classifier was trained on a number of features parallel to Lee and Yeung [76]. These being, the target word's ranking in a Chinese proficiency test 14 , word length, word frequency in the Chinese Wikipedia Corpus [76] and the Jinan Corpus of Learner Chinese (JCLC) [140], along with Chinese character frequency in the JCLC. They discovered that their logistic regression models outperformed Lee and Yeung [76]'s prior SVM.…”

Section: 21mentioning

confidence: 99%

Lexical Complexity Prediction: An Overview

2023

View full text Add to dashboard Cite

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

“…Using this self-assessment as training data, the system performs Complex Word Identification (Yimam et al, 2018) to construct the user's vocabulary set. Our model, which automatically predicts each L2 word as either known or unknown to the user with an SVM classifier, performs at 78.0% accuracy (Lee & Yeung, 2018). New users may also opt out of self-assessment and manually choose a rough vocabulary set size.…”

Section: Learner Modelmentioning

confidence: 99%

An editable learner model for text recommendation for language learning

Lee¹

2021

ReCALL

View full text Add to dashboard Cite

Extracurricular reading is important for learning foreign languages. Text recommendation systems typically classify users and documents into levels, and then match users with documents at the same level. Although this approach can be effective, it has two significant shortcomings. First, the levels assume a standard order of language acquisition and cannot be personalized to the users’ learning patterns. Second, recommendation decisions are not transparent because the leveling algorithms can be difficult for users to interpret. We propose a novel method for text recommendation that addresses these two issues. To enhance personalization, an open, editable learner model estimates user knowledge of each word in the foreign language. The documents are ranked by new-word density (NWD) – that is, the percentage of words that are new to the user in the document. The system then recommends documents according to a user-specified target NWD. This design offers complete transparency as users can scrutinize recommendations by reviewing the NWD estimation of the learner model. This article describes an implementation of this method in a mobile app for learners of Chinese as a foreign language. Evaluation results show that users were able to manipulate the learner model and NWD parameters to adjust the difficulty of the recommended documents. In a survey, users reported satisfaction with both the concept and implementation of this text recommendation method.

show abstract

Automatic prediction of vocabulary knowledge for learners of Chinese as a foreign language

Cited by 6 publications

References 8 publications

Predicting academic performance: a systematic literature review

Predicting academic performance: a systematic literature review

Lexical Complexity Prediction: An Overview

An editable learner model for text recommendation for language learning

Contact Info

Product

Resources

About