{"id":"W4402206897","doi":"10.1016/j.nlp.2024.100102","title":"Job description parsing with explainable transformer based ensemble models to extract the technical and non-technical skills","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Computer science; Margin (machine learning); Artificial intelligence; Machine learning; Transformer; Statistical model; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005089268,0.0009084745,0.0003600557,0.001221559,0.0002978574,0.0005524976,0.0009659869,0.0006872932,0.002385336],"category_scores_gemma":[0.001545449,0.0003014377,0.001164054,0.001043017,0.0002124727,0.001460251,0.0008710432,0.001352352,0.001257106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006370504,"about_ca_system_score_gemma":0.0009670905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01268134,"about_ca_topic_score_gemma":0.02418,"domain_scores_codex":[0.9997956,0.00003869209,0.00001272866,0.0000858257,0.00003635396,0.00003075667],"domain_scores_gemma":[0.9995199,0.0002477315,0.00003526175,0.00006877918,0.0001024838,0.00002583887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004296474,0.0004443718,0.01988093,0.0003434306,0.0002747146,0.000777702,0.0006151745,0.2733017,0.01668289,0.009728899,0.03053517,0.6469854],"study_design_scores_gemma":[0.000009581355,0.00003874311,0.002029916,0.00002115235,0.0000566014,0.00007824958,0.00005947211,0.9855508,0.003505217,0.004753726,0.003881671,0.00001480122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1791666,0.001530385,0.7872555,0.0009602274,0.0002817479,0.0002252662,0.007499724,0.01451239,0.008568143],"genre_scores_gemma":[0.7903439,0.0007190886,0.1775637,0.000350965,0.0001002814,0.0002327828,0.01868251,0.0003752851,0.01163155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01268134,"threshold_uncertainty_score":0.02521503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01353790584292541,"score_gpt":0.2620085156993179,"score_spread":0.2484706098563925,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}