A Methodology for Multilingual Automatic Item Generation

2016 ◽  
Vol 37 (3) ◽  
pp. 39-61 ◽  
Author(s):  
Mark J. Gierl ◽  
Hollis Lai
Keyword(s):  
Computer Technology ◽  
Test Development ◽  
Cost Effective ◽  
Computer Algorithms ◽  
Timely Manner ◽  
Item Generation ◽  
Assessment Task ◽  
Test Items ◽  
Large Numbers ◽  
Automatic Item Generation

Testing agencies require large numbers of high-quality items that are produced in a cost-effective and timely manner. Increasingly, these agencies also require items in different languages. In this paper we present a methodology for multilingual automatic item generation (AIG). AIG is the process of using item models to generate test items with the aid of computer technology. We describe a three-step AIG approach where, first, test development specialists identify the content that will be used for item generation. Next, the specialists create item models to specify the content in the assessment task that must be manipulated to produce new items. Finally, elements in the item model are manipulated with computer algorithms to produce new items. Language is added in the item model step to permit multilingual AIG. We illustrate our method by generating 360 English and 360 French medical education items. The importance of item banking in multilingual test development is also discussed.

scholarly journals Using Automatic Item Generation to Create Solutions and Rationales for Computerized Formative Testing

2017 ◽  
Vol 42 (1) ◽  
pp. 42-57 ◽  
Author(s):  
Mark J. Gierl ◽  
Hollis Lai
Keyword(s):  
Computer Technology ◽  
Research Area ◽  
Computerized Testing ◽  
Item Generation ◽  
Test Items ◽  
Item Development ◽  
Large Numbers ◽  
Modeling Practices ◽  
Automatic Item Generation ◽  
Formative Testing

Computerized testing provides many benefits to support formative assessment. However, the advent of computerized formative testing has also raised formidable new challenges, particularly in the area of item development. Large numbers of diverse, high-quality test items are required because items are continuously administered to students. Hence, hundreds of items are needed to develop the banks necessary for computerized formative testing. One promising approach that may be used to address this test development challenge is automatic item generation. Automatic item generation is a relatively new but rapidly evolving research area where cognitive and psychometric modeling practices are used to produce items with the aid of computer technology. The purpose of this study is to describe a new method for generating both the items and the rationales required to solve the items to produce the required feedback for computerized formative testing. The method for rationale generation is demonstrated and evaluated in the medical education domain.

Automatic Item Generation

2018 ◽  
pp. 2369-2379 ◽  
Author(s):  
Mark Gierl ◽  
Hollis Lai ◽  
Xinxin Zhang
Keyword(s):  
Computer Technology ◽  
Health Sciences ◽  
Design And Development ◽  
Specific Test ◽  
Item Generation ◽  
Test Items ◽  
Medical Health ◽  
Automatic Item Generation ◽  
Educational Tests

Changes to the design and development of educational tests are resulting in the unprecedented demand for a large supply of content-specific test items. One way to address this growing demand is with automatic item generation. Automatic item generation is the process of using models to create test items with the aid of computer technology. The purpose of this chapter is to describe and illustrate a method for generating test items. The method is also illustrated using an example from the medical health sciences.

Automatic Item Generation

2019 ◽  
pp. 192-203 ◽  
Author(s):  
Mark Gierl ◽  
Hollis Lai ◽  
Xinxin Zhang
Keyword(s):  
Computer Technology ◽  
Health Sciences ◽  
Design And Development ◽  
Specific Test ◽  
Item Generation ◽  
Test Items ◽  
Medical Health ◽  
Automatic Item Generation ◽  
Educational Tests

Changes to the design and development of educational tests are resulting in the unprecedented demand for a large supply of content-specific test items. One way to address this growing demand is with automatic item generation. Automatic item generation is the process of using models to create test items with the aid of computer technology. The purpose of this chapter is to describe and illustrate a method for generating test items. The method is also illustrated using an example from the medical health sciences.

Volunteer Science

2016 ◽  
Vol 79 (4) ◽  
pp. 376-396 ◽  
Author(s):  
Jason Radford ◽  
Andy Pilny ◽  
Ashley Reichelmann ◽  
Brian Keegan ◽  
Brooke Foucault Welles ◽  
...  
Keyword(s):  
Large Scale ◽  
Effective Means ◽  
Cost Effective ◽  
Social Psychological ◽  
Timely Manner ◽  
Online Laboratory ◽  
Large Numbers ◽  
Large Scale Survey ◽  
Online Methods ◽  
Psychological Experiments

Experimental research in traditional laboratories comes at a significant logistic and financial cost while drawing data from demographically narrow populations. The growth of online methods of research has resulted in effective means for social psychologists to collect large-scale survey-based data in a cost-effective and timely manner. However, the same advancement has not occurred for social psychologists who rely on experimentation as their primary method of data collection. The aim of this article is to provide an overview of one online laboratory for conducting experiments, Volunteer Science, and report the results of six studies that test canonical behaviors commonly captured in social psychological experiments. Our results show that the online laboratory is capable of performing a variety of studies with large numbers of diverse volunteers. We advocate for the use of the online laboratory as a valid and cost-effective way to perform social psychological experiments with large numbers of diverse subjects.

Automating the Generation of Test Items

2021 ◽  
pp. 233-244
Author(s):  
Hollis Lai ◽  
Mark Gierl
Keyword(s):  
Health Sciences ◽  
Complex Problem ◽  
Future Research ◽  
Item Generation ◽  
Test Items ◽  
Computerized Assessments ◽  
Medical Health ◽  
Increasing Demand ◽  
Automatic Item Generation ◽  
Content Specialists

Increasing demand for knowledge of our workers has prompted the increase in assessments and providing feedback to facilitate their learning. This and the increasingly computerized assessments require new test items beyond the ability for content specialists to produce them in a feasible fashion. Automatic item generation is a promising method that has begun to demonstrate utility in its application. The purpose of this chapter is to describe how AIG can be used to generate test items using the selected-response (i.e., multiple-choice) format. To ensure our description is both concrete and practical, we illustrate template-based item generation using an example from the complex problem-solving domain of the medical health sciences. The chapter is concluded with a description of the two directions for future research.

Outside the Box: Innovative Application of Diversion as a Replacement for Bridge Plug

2021 ◽  
Author(s):  
Hong Chang ◽  
De Qiang Yi ◽  
Yang Lv ◽  
Ming Zhao ◽  
Peng Liang Cao ◽  
...  
Keyword(s):  
Ordos Basin ◽  
Cost Effective ◽  
Vital Role ◽  
Remedial Action ◽  
Timely Manner ◽  
Particle Fracture ◽  
Sand Body ◽  
Remedial Actions ◽  
Treatment Analysis ◽  
Casing Deformation

Abstract Effective stage-to-stage isolation is typically accomplished by setting a bridge plug in a properly cemented casing between stages. This isolation plays a vital role in a horizontal well multistage fracturing completion. Failure of isolation not only impacts the well productivity but also wastes fracturing materials. The challenges isolation failure poses for stimulation effectiveness include both detection and remediation. First, there has been historically no reliable and cost-effective solution to detect stage-to-stage isolation onsite. One may only start to realize this problem when inconsistent production is observed. Second, existing remedial actions are seldom satisfying in case of an isolation failure. Most commonly, a new plug is set to replace the failed one. However, because the perforation clusters of an unstimulated stage may create irregularities in well inside diameter (ID) (e.g., casing deformation or burr), there is a risk that the plug will be damaged or become stuck when it passes the perforation area. Also, when the plug passes a perforation cluster, the perforations start to take in the pump-down fluid, which can increase the difficulty of the pump-down job. A novel remedial action uses high-frequency pressure monitoring (HFPM) and diversion to solve both challenges. The stage isolation integrity is evaluated in quasi-real time by analyzing the water hammer after the pump shutdown. In the case of a plug failure, large-particle fracture diversion materials and techniques can establish temporary wellbore isolation through a quick and simple delivery process. To close the cycle, the effect of the diversion can be evaluated by HFPM, which can reveal the fluid entry point of the treatment fluid after diversion. The technique was applied to two cases in Ordos basin in which wellbore isolation failure interrupted the operation. The problem identification, development of the solution workflow, and observation from treatment analysis are discussed. In both cases, the stage-to-stage isolation was recovered, and the drilled sand body was successfully stimulated without involving costly and time-consuming well intervention. The stimulation operation of the entire well was successfully resumed in a timely manner.

scholarly journals The High Capacity Expanding Lifeboat HiCEL – Meeting the Modern SAR Challenge

2018 ◽  
Author(s):  
J R E Wright ◽  
G E Payne
Keyword(s):  
Large Scale ◽  
High Capacity ◽  
Cost Effective ◽  
Second World War ◽  
Concept Design ◽  
Small Vessels ◽  
Large Numbers ◽  
Cost Effective Alternative ◽  
Operational Envelope ◽  
Second World

The Mediterranean migrant crisis has resulted in the highest population displacement since the Second World War. In 2016 alone, over one million made the journey across the sea. Since 2013 over 15,000 have died as a result of this journey. Small vessels such as wooden fishing boats and RIBs are commonly used by smugglers as transport. These are often unseaworthy and filled with numbers of passengers far exceeding their intended capacity. When failure occurs, rescues are typically conducted by the nearest available vessel. These vessels are often ill-equipped for a large-scale Search and Rescue (SAR) operation making it highly dangerous for all involved.  The size and quantity of lifeboats available are often insufficient for the large numbers of people to be rescued; as a result, repeat journeys are required, making the rescue process slow, inefficient and hazardous. This paper outlines a novel solution to this problem. A concept design is presented for a rapidly expandable lifeboat capable of holding large numbers of passengers, whilst still fitting into the operational envelope of common davits. The unique inflatable design can be deployed quickly from a range of vessels and aeroplanes offering an immediate platform from which disembarkation onto a suitable vessel can be achieved. CONOPS are outlined along with the required capabilities of the design. Drop stitch technology is identified as a viable means of manufacturing the large inflatable platforms. Finally, the paper discusses an alternative solution, retrofitting existing enclosed lifeboats with the solution to offer a more cost-effective alternative.  

Advanced Methods in Automatic Item Generation

2021 ◽  
Author(s):  
Mark J. Gierl ◽  
Hollis Lai ◽  
Vasily Tanygin
Keyword(s):  
Item Generation ◽  
Automatic Item Generation

Three Modeling Applications to Promote Automatic Item Generation for Examinations in Dentistry

2016 ◽  
Vol 80 (3) ◽  
pp. 339-347 ◽  
Author(s):  
Hollis Lai ◽  
Mark J. Gierl ◽  
B. Ellen Byrne ◽  
Andrew I. Spielman ◽  
David M. Waldschmidt
Keyword(s):  
Item Generation ◽  
Automatic Item Generation
Sign in / Sign up

Export Citation Format

Share Document