Advancing Natural Language Processing in Educational Assessment

Advancing Natural Language Processing in Educational Assessment examines the use of natural language technology in educational testing, measurement, and assessment. Recent developments in natural language processing (NLP) have enabled large-scale educational applications, though scholars and professionals may lack a shared understanding of the strengths and limitations of NLP in assessment as well as the challenges that testing organizations face in implementation. This first-of-its-kind book provides evidence-based practices for the use of NLP-based approaches to automated text and speech scoring, language proficiency assessment, technology-assisted item generation, gamification, learner feedback, and beyond. Spanning historical context, validity and fairness issues, emerging technologies, and implications for feedback and personalization, these chapters represent the most robust treatment yet about NLP for education measurement researchers, psychometricians, testing professionals, and policymakers. The Open Access version of this book, available at www.taylorfrancis.com, has been made available under a Creative Commons Attribution-NonCommercial-No Derivatives 4.0 license.

Victoria Yaneva is Senior NLP Scientist at the National Board of Medical Examiners, USA. Matthias von Davier is Monan Professor of Education in the Lynch School of Education and Executive Director of TIMSS & PIRLS International Study Center at Boston College, USA.

Preface by Victoria Yaneva and Matthias von Davier Section I: Automated Scoring Chapter 1: The Role of Robust Software in Automated Scoring by Nitin Madnani, Aoife Cahill, and Anastassia Loukina Chapter 2: Psychometric Considerations when Using Deep Learning for Automated Scoring by Susan Lottridge, Chris Ormerod, and Amir Jafari Chapter 3: Speech Analysis in Assessment by Jared C. Bernstein and Jian Cheng Chapter 4: Assessment of Clinical Skills: A Case Study in Constructing an NLP-Based Scoring System for Patient Notes by Polina Harik, Janet Mee, Christopher Runyon, and Brian E. Clauser Section II: Item Development Chapter 5: Automatic Generation of Multiple-Choice Test Items from Paragraphs Using Deep Neural Networks by Ruslan Mitkov, Le An Ha, Halyna Maslak, Tharindu Ranasinghe, and Vilelmini Sosoni Chapter 6: Training Optimus Prime, M.D.: A Case Study of Automated Item Generation using Artificial Intelligence - From Fine-Tuned GPT2 to GPT3 and Beyond by Matthias von Davier Chapter 7: Computational Psychometrics for Digital-first Assessments: A Blend of ML and Psychometrics for Item Generation and Scoring by Geoff LaFlair, Kevin Yancey, Burr Settles, Alina A von Davier Section III: Validity and Fairness Chapter 8: Validity, Fairness, and Technology-based Assessment by Suzanne Lane Chapter 9: Evaluating Fairness of Automated Scoring in Educational Measurement by Matthew S. Johnson and Daniel F. McCaffrey Section IV: Emerging Technologies Chapter 10: Extracting Linguistic Signal from Item Text and Its Application to Modeling Item Characteristics by Victoria Yaneva, Peter Baldwin, Le An Ha, and Christopher Runyon Chapter 11: Stealth Literacy Assessment: Leveraging Games and NLP in iSTART by Ying Fang, Laura K. Allen, Rod D. Roscoe, and Danielle S. McNamara Chapter 12: Measuring Scientific Understanding Across International Samples: The Promise of Machine Translation and NLP-based Machine Learning Technologies by Minsu Ha and Ross H. Nehm Chapter 13: Making Sense of College Students' Writing Achievement and Retention with Automated Writing Evaluation by Jill Burstein, Daniel McCaffrey, Steven Holtzman & Beata Beigman Klebanov Contributor Biographies