{"id":"W2795302121","doi":"10.1109/icde.2018.00093","title":"Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Schema (genetic algorithms); Knowledge graph; Semantics (computer science); Linked data; Information retrieval; Semantic Web; Word (group theory); RDF; Distributional semantics; Natural language processing; Semantic similarity; 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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00586649,0.0001410183,0.0002499748,0.0001939785,0.0004213437,0.001793432,0.002906196,0.00004840629,0.0002087417],"category_scores_gemma":[0.002537817,0.0001070159,0.00005186133,0.0004483657,0.0001562822,0.004182257,0.003592124,0.0000696452,0.0002593401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002378588,"about_ca_system_score_gemma":0.00004792117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001331034,"about_ca_topic_score_gemma":0.0004124949,"domain_scores_codex":[0.9970962,0.00009177249,0.0006427289,0.0009202744,0.0008759178,0.0003731115],"domain_scores_gemma":[0.9957684,0.001003538,0.0002447605,0.002778396,0.000127052,0.00007786896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009968696,0.000161485,0.002218245,0.0001060045,0.0001459234,0.00001245342,0.0009112635,0.00007543709,0.0009314037,0.07507817,0.7434011,0.1768588],"study_design_scores_gemma":[0.0003101434,0.00003484496,0.000268917,0.00008589038,0.00004894716,0.000003424387,0.001551587,0.1976278,0.0004755246,0.02530724,0.7740192,0.0002665028],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01744589,0.00002235465,0.9766752,0.00102297,0.0008881675,0.0003191295,0.002067088,0.00005565959,0.001503556],"genre_scores_gemma":[0.6047588,0.00002475149,0.3739181,0.008209795,0.001927518,0.00001122734,0.005359818,0.00004993685,0.005740017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.602757,"threshold_uncertainty_score":0.9992428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4932316803399396,"score_gpt":0.519707133187662,"score_spread":0.0264754528477224,"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."}}