ACM Logo  An ACM Publication  |  CONTRIBUTE  |  FOLLOW    

RECENT ARTICLES



More

RECENT OPINIONS

Getting Authoring Right: How to innovate for meaningful improvement

By Alice Leigh, Shaun Crowley

With so much technology-enabled innovation in assessment, one area has often had too little attention--the exam development phase, often called the "hardest job in publishing." Writing exams is so challenging and so important, not just for the validity of tests but also for the ability of exam providers to innovate their services and operate efficiently. With genuinely enterprise scale solutions finally becoming available in this area, the authors offer a checklist guide for assessment providers to review their authoring processes.


Harnessing the Power of Natural Language Processing to Mass Produce Test Items

By Martin C. Yu, Taylor Sullivan

Mass production of test items involves numerous steps and takes time. Technology can play a key role in supplementing human resources whether gathering and storing source materials, communicating with subject matter experts, or synchronizing and coordinating activities during a complex or fast-paced development cycle. Our work in automated item generation (AIG) using natural language processing is one example of this process unfolding in practice. Over the past few years, there has been a surge in developments in the fields of natural language understanding and generation (NLU/NLG) regarding applications of language models developed via machine learning techniques that have yet to be applied to the area of AIG.