{"id":"W1980720057","doi":"10.1007/s00500-015-1632-6","title":"Feature-driven linguistic-based entity matching in linked data with application in pharmacy","year":2015,"lang":"en","type":"article","venue":"Soft Computing","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"SPARQL; Computer science; RDF; Process (computing); Linked data; Feature (linguistics); Information retrieval; Natural language; Hyperlink; Semantic Web; Natural language processing; World Wide Web; Web page; Linguistics; Programming language","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":[0.00294954,0.000351636,0.0007488257,0.003751352,0.0009196917,0.002541103,0.001507561,0.001263356,0.002074277],"category_scores_gemma":[0.01375766,0.000303311,0.001306071,0.005249443,0.0004039623,0.002526294,0.001937525,0.0008046653,0.0007630058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009275913,"about_ca_system_score_gemma":0.001666807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01068699,"about_ca_topic_score_gemma":0.01461314,"domain_scores_codex":[0.9976307,0.0008014906,0.000274253,0.0005131536,0.0006216097,0.0001587394],"domain_scores_gemma":[0.9942015,0.003611916,0.0004317662,0.0005902502,0.001023406,0.000141127],"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":[0.001709584,0.001405294,0.06484883,0.001310813,0.000601426,0.001816077,0.001161903,0.2143304,0.01688461,0.02158714,0.01370417,0.6606398],"study_design_scores_gemma":[0.00003604837,0.00009404313,0.007629949,0.00004229714,0.0001037529,0.0002265142,0.0002974439,0.96706,0.007223845,0.01296449,0.004285772,0.00003584266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3414729,0.001069236,0.6394137,0.001372174,0.0002043187,0.0005200942,0.007007973,0.004716886,0.004222745],"genre_scores_gemma":[0.7032872,0.0002484341,0.2892092,0.0001588888,0.00004607626,0.000148195,0.005607912,0.0001204581,0.001173593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01068699,"threshold_uncertainty_score":0.02124959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2202229176735751,"score_gpt":0.4482172416113033,"score_spread":0.2279943239377282,"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."}}