{"id":"W2170688652","doi":"10.1007/s00778-007-0067-9","title":"Applications of corpus-based semantic similarity and word segmentation to database schema matching","year":2007,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Schema matching; Computer science; Semantic similarity; Artificial intelligence; Schema (genetic algorithms); Star schema; Natural language processing; Information retrieval; Segmentation; Pattern recognition (psychology); Database schema; Data mining; Data integration","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":[],"consensus_categories":[],"category_scores_codex":[0.01106816,0.00006629908,0.0001212214,0.0002060113,0.0003059042,0.0002015666,0.0005133172,0.00001718022,0.00010555],"category_scores_gemma":[0.0003647562,0.00004171928,0.00003530759,0.0004948014,0.00007142599,0.0002618133,0.0001773229,0.0001464765,0.00004210326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001947723,"about_ca_system_score_gemma":0.00003012122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004580274,"about_ca_topic_score_gemma":0.0001438703,"domain_scores_codex":[0.9982775,0.000142833,0.0004982671,0.0001546767,0.0007799368,0.000146818],"domain_scores_gemma":[0.9982492,0.0008003096,0.0002847238,0.0004223816,0.0001284795,0.0001148897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002343741,0.0002385743,0.003697193,0.00004386875,0.00004885914,0.00001470202,0.001793554,0.0008332114,0.01886816,0.0137209,0.0099991,0.9505075],"study_design_scores_gemma":[0.005357501,0.0004521797,0.1266931,0.0004456205,0.0003885247,0.0003067153,0.0356785,0.005412393,0.06898663,0.3467853,0.408431,0.001062554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2572511,0.0000738708,0.7390159,0.00314619,0.00007167492,0.0002022231,0.0000286172,0.000006884361,0.0002035413],"genre_scores_gemma":[0.9720079,0.00003662732,0.02589044,0.00175214,0.0001009199,0.000005604817,0.000009905852,0.000005636267,0.0001908711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9494449,"threshold_uncertainty_score":0.3836027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1166235600128447,"score_gpt":0.4294959857511475,"score_spread":0.3128724257383028,"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."}}