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

English proficiency assessments have become a necessary metric for filteringand selecting prospective candidates for both academia and industry. With therise in demand for such assessments, it has become increasingly necessary tohave the automated human-interpretable results to prevent inconsistencies andensure meaningful feedback to the second language learners. Feature-basedclassical approaches have been more interpretable in understanding what thescoring model learns. Therefore, in this work, we utilize classical machinelearning models to formulate a speech scoring task as both a classification anda regression problem, followed by a thorough study to interpret and study therelation between the linguistic cues and the English proficiency level of thespeaker. First, we extract linguist features under five categories (fluency,pronunciation, content, grammar and vocabulary, and acoustic) and train modelsto grade responses. In comparison, we find that the regression-based modelsperform equivalent to or better than the classification approach. Second, weperform ablation studies to understand the impact of each of the feature andfeature categories on the performance of proficiency grading. Further, tounderstand individual feature contributions, we present the importance of topfeatures on the best performing algorithm for the grading task. Third, we makeuse of Partial Dependence Plots and Shapley values to explore featureimportance and conclude that the best performing trained model learns theunderlying rubrics used for grading the dataset used in this study.

Automated Speech Scoring System Under The Lens: Evaluating and interpreting the linguistic cues for language proficiency