English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Corpora and web texts can become a rich language learning resource if we havea means of assessing whether they are linguistically appropriate for learnersat a given proficiency level. In this paper, we aim at addressing this issue bypresenting the first approach for predicting linguistic complexity for Swedishsecond language learning material on a 5-point scale. After showing that thetraditional Swedish readability measure, L\"asbarhetsindex (LIX), is notsuitable for this task, we propose a supervised machine learning model, basedon a range of linguistic features, that can reliably classify texts accordingto their difficulty level. Our model obtained an accuracy of 81.3% and anF-score of 0.8, which is comparable to the state of the art in English and isconsiderably higher than previously reported results for other languages. Wefurther studied the utility of our features with single sentences instead offull texts since sentences are a common linguistic unit in language learningexercises. We trained a separate model on sentence-level data with fiveclasses, which yielded 63.4% accuracy. Although this is lower than the documentlevel performance, we achieved an adjacent accuracy of 92%. Furthermore, wefound that using a combination of different features, compared to using lexicalfeatures alone, resulted in 7% improvement in classification accuracy at thesentence level, whereas at the document level, lexical features were moredominant. Our models are intended for use in a freely accessible web-basedlanguage learning platform for the automatic generation of exercises.

A Readable Read: Automatic Assessment of Language Learning Materials based on Linguistic Complexity