MétaCan
Menu
Back to cohort
Record W4402206897 · doi:10.1016/j.nlp.2024.100102

Job description parsing with explainable transformer based ensemble models to extract the technical and non-technical skills

2024· article· en· W4402206897 on OpenAlex

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.

Bibliographic record

VenueNatural Language Processing Journal · 2024
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsCarleton University
Fundersnot available
KeywordsInterpretabilityComputer scienceMargin (machine learning)Artificial intelligenceMachine learningTransformerStatistical modelEngineering

Abstract

fetched live from OpenAlex

The rapid digitization of the economy is transforming the job market, creating new roles and reshaping existing ones. As skill requirements evolve, identifying essential competencies becomes increasingly critical. This paper introduces a novel ensemble model that combines traditional and transformer-based neural networks to extract both technical and non-technical skills from job descriptions. A substantial dataset of job descriptions from reputable platforms was meticulously annotated for 22 IT roles. The model demonstrated superior performance in extracting both non-technical (67% F-score) and technical skills (72% F-score) compared to conventional CRF and hybrid deep learning models. Specifically, the proposed model outperformed these baselines by an average margin of 10% and 6%, respectively, for non-technical skills, and 29% and 6.8% for technical skills. A 5 × 2cv paired t-test confirmed the statistical significance of these improvements. In addition, to enhance model interpretability, Local Interpretable Model-Agnostic Explanations (LIME) were employed in the experiments.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.982
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0020.002
Open science0.0010.000
Research integrity0.0000.001
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 head0.014
GPT teacher head0.262
Teacher spread0.248 · 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