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

Computerized Adaptive Testing (CAT) is emerging as a promising testingapplication in many scenarios, such as education, game and recruitment, whichtargets at diagnosing the knowledge mastery levels of examinees on requiredconcepts. It shows the advantage of tailoring a personalized testing procedurefor each examinee, which selects questions step by step, depending on herperformance. While there are many efforts on developing CAT systems, existingsolutions generally follow an inflexible model-specific fashion. That is, theyneed to observe a specific cognitive model which can estimate examinee'sknowledge levels and design the selection strategy according to the modelestimation. In this paper, we study a novel model-agnostic CAT problem, wherewe aim to propose a flexible framework that can adapt to different cognitivemodels. Meanwhile, this work also figures out CAT solution with addressing theproblem of how to generate both high-quality and diverse questionssimultaneously, which can give a comprehensive knowledge diagnosis for eachexaminee. Inspired by Active Learning, we propose a novel framework, namelyModel-Agnostic Adaptive Testing (MAAT) for CAT solution, where we design threesophisticated modules including Quality Module, Diversity Module and ImportanceModule. Extensive experimental results on two real-world datasets clearlydemonstrate that our MAAT can support CAT with guaranteeing both quality anddiversity perspectives.

Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing