MétaCan
Menu
Back to cohort
Record W2460844011 · doi:10.7202/1036327ar

A Methodology for Multilingual Automatic Item Generation

2016· article· en· W2460844011 on OpenAlex
Mark J. Gierl, Hollis Lai

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
venuePublished in a venue whose home country is Canada.

Bibliographic record

VenueMesure et évaluation en éducation · 2016
Typearticle
Languageen
FieldComputer Science
TopicEducational Technology and Assessment
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsComputer scienceItem bankTask (project management)Test (biology)Process (computing)Quality (philosophy)Item response theoryNatural language processingMultilingualismArtificial intelligenceInformation retrievalPsychometricsPsychologyProgramming language

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.575
Threshold uncertainty score0.354

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0090.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.240
GPT teacher head0.468
Teacher spread0.228 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it