{"id":"W2250657762","doi":"","title":"Clustering Semantically Equivalent Words into Cognate Sets in Multilingual Lists","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cognate; Computer science; Word (group theory); Natural language processing; Artificial intelligence; Cluster analysis; ENCODE; Similarity (geometry); Mathematics; Linguistics","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":[0.0003975753,0.0001565913,0.0001627923,0.0001793271,0.000046726,0.000100768,0.001045279,0.00009314268,0.00003903913],"category_scores_gemma":[0.000105703,0.0001309991,0.0000396505,0.0003297436,0.00005079299,0.0004782611,0.0009117753,0.0002307026,0.00002832589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005875881,"about_ca_system_score_gemma":0.00004649517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000394626,"about_ca_topic_score_gemma":0.0003690711,"domain_scores_codex":[0.9986864,0.00004658371,0.0002814345,0.0004121317,0.0002321948,0.0003412858],"domain_scores_gemma":[0.9993231,0.00004415233,0.00005810061,0.0004160472,0.00007032579,0.00008828881],"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":[0.00007200338,0.0004052423,0.003900327,0.0003048786,0.00002569666,0.001100806,0.04747747,0.00001007023,0.01608522,0.03810536,0.0001692704,0.8923436],"study_design_scores_gemma":[0.001324313,0.0003476651,0.003873229,0.000804243,0.00001285443,0.0001535372,0.000343156,0.4057579,0.4134706,0.1723042,0.0001219266,0.001486299],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05726619,0.0004954759,0.9357842,0.0002375638,0.0002467868,0.0001858187,3.058531e-7,0.00111319,0.004670526],"genre_scores_gemma":[0.5306666,0.000004247453,0.4690135,0.0002046154,0.00001023962,0.000005427547,3.655362e-7,0.000006436041,0.00008852631],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8908573,"threshold_uncertainty_score":0.5341988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03354109724348471,"score_gpt":0.3110713321578363,"score_spread":0.2775302349143516,"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."}}