Maryland Assessment Research Center (MARC)

2017 MARC Conference

The Seventeenth Annual Maryland Assessment Conference:

Application of Artificial Intelligence (AI) to Assessment

The following topics will be included in this conference:
(a) Automated Adaptive Testing
(b) Automated Scoring
(c) Automated Item Generation
(d) Automated Form Assembly

  • Jointly supported by the Maryland State Department of Education and the Maryland Assessment Research Center. 
  • Each topic will be given a one-hour block of time, including a 50-minute presentation by each speaker followed by 10 minutes of Q and A.

Presentation Schedule

 

Thursday, November 2nd, 2017

TimeTitlePresenter(s)
7:00-8:30Registration and Breakfast
8:30-8:45Welcome and CommentsHong Jiao (University of Maryland)
8:45-9:45Generating Test Items for English Language Arts
Presentation Slides
Mark Gierl & Hollis Lai (University of Alberta)
9:45-10:45Difficulty, Item and Response Modeling: An Intersection of AI and Assessment
Presentation Slides
Issac Bejar & Michael Flor (Educational Testing Services)
10:45-11:00Break
11:00-12:00Reconceptualizing Items: From Clones and Automatic Item Generation to Task Model Families
Presentation Slides
Richard Luecht (University of North Carolina, Greensboro)&
Matt Burke (American Board of Internal Medicine)
12:00-1:00Lunch
1:00-2:00Estimating Person Characteristics from Voice, Speech, Language and Touch
Presentation Slides
Jared Bernstein (Stanford University) &
Jian Cheng (Analytic Measures Inc.)
2:00-3:00Addressing Literacy with Natural Language Processing
Presentation Slides
Jill Burstein (Educational Testing Services)
3:00-3:15Break
3:15-4:15Practical Considerations for Implementing Automated Scoring of Writing for Large-Scale Use
Presentation Slides
Peter Foltz (Pearson and University of Colorado, Boulder)
4:15-5:15Constructing LOFT Item Pools with Linear Programming
Presentation Slides
Jeffrey Patton & Ray Y. Yan (Financial Industry Regulatory Authority)

Friday, November 3rd, 2017

7:00-8:30Registration and Breakfast
8:30-9:30Case Studies in Automated Test Assembly in Classical Test Theory and Item Response Theory Contexts
Presentation Slides
Luz Bay, David Chuah & Thomas P. Proctor (The College Board)
9:30-10:30Computerized Multistage Testing and its Applications
Presentation Slides
Duanli Yan (Educational Testing Service)
10:30-10:45Break
10:45-11:45An Intelligent CAT that Can Deal with Disengaged Test Taking
Presentation Slides
Steven Wise (Northwest Evaluation Association)
11:45-12:45Differences in the Amount of Adaptation of Computerized Adaptive Tests, Stratified Adaptive Tests and Multistage Tests
Presentation Slides
Mark D. Reckase, Unhee Ju & Sewon Kim (Michigan State University)
12:45-1:00Closing Comments Robert Lissitz (University of Maryland)
 

Automatic Item Generation with Artificial Intelligence: The AIG of AI, by AI, and for AI.


(Note: This paper is not to be presented at the conference but will be included in a book based on the conference)
 

Jaehwa Choi (George Washington University)