{"id":"W4414042672","doi":"10.1007/978-3-032-05607-8_19","title":"Hybrid Ontology Matching for Company Name Alignment: Combining Text Matching, String Similarity, SBERT, and Siamese Networks in Italian and German Job Market Data","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Matching (statistics); Discriminative model; Normalization (sociology); Ontology; Robustness (evolution); String searching algorithm; Ontology alignment; Cosine similarity; String (physics); String metric","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":[0.002008577,0.0005383721,0.0006965764,0.007668624,0.0009141737,0.001850076,0.001001617,0.0008331256,0.002955288],"category_scores_gemma":[0.005265151,0.00021417,0.001104046,0.008391941,0.0003559729,0.003397595,0.001520878,0.000615718,0.002481936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008575946,"about_ca_system_score_gemma":0.001456041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02072836,"about_ca_topic_score_gemma":0.0424734,"domain_scores_codex":[0.9983789,0.0005008044,0.000194762,0.0004184016,0.0003410382,0.000166246],"domain_scores_gemma":[0.9980332,0.001084509,0.0001495685,0.0003565134,0.0002979943,0.00007817717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007110219,0.0007060703,0.05785137,0.0006008822,0.0004925603,0.0004203319,0.0006738128,0.02670142,0.01509054,0.01332862,0.05845299,0.8249704],"study_design_scores_gemma":[0.0001152187,0.0001645286,0.0576818,0.0001621308,0.0004023693,0.0006649774,0.001655964,0.8273269,0.01727208,0.0419971,0.05244345,0.0001134656],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5197698,0.003745496,0.3944722,0.001346065,0.0003422904,0.0003784051,0.04673211,0.01566992,0.0175438],"genre_scores_gemma":[0.5972571,0.00115235,0.289571,0.0001866205,0.0002093024,0.0002396709,0.1036116,0.0009699408,0.00680242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02072836,"threshold_uncertainty_score":0.04121542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02314462661599339,"score_gpt":0.2758699511476817,"score_spread":0.2527253245316883,"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."}}