{"id":"W2077811574","doi":"10.3115/1073336.1073350","title":"Identifying cognates by phonetic and semantic similarity","year":2001,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Pennsylvania","keywords":"WordNet; Computer science; Similarity (geometry); Artificial intelligence; Natural language processing; Semantic similarity; Longest common subsequence problem; Selection (genetic algorithm); Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000145028,0.00008741621,0.00008929399,0.00005262511,0.00009085749,0.0002782134,0.000400137,0.00004615357,0.00002281805],"category_scores_gemma":[0.00003591347,0.00007212189,0.00001546719,0.0002274903,0.0000366526,0.0004363238,0.0002555227,0.0001056161,0.00001073606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001062093,"about_ca_system_score_gemma":0.000008585641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000935912,"about_ca_topic_score_gemma":0.00001411177,"domain_scores_codex":[0.9993029,0.00002055478,0.0001027949,0.0002573033,0.0001411,0.0001753652],"domain_scores_gemma":[0.9996228,0.00004540175,0.00003261953,0.0002098417,0.00003656153,0.00005284172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001629085,0.0002838367,0.02254538,0.0003218013,0.00006222759,0.0004302356,0.003216793,0.000001174643,0.2773,0.09658436,0.05402422,0.5452136],"study_design_scores_gemma":[0.000686328,0.0001255965,0.002460759,0.0001944164,0.00002550779,0.0005556922,0.00009462264,0.05931167,0.4178984,0.5133289,0.004285838,0.001032258],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03406208,0.007215427,0.9555049,0.001334967,0.00006841243,0.00008397262,4.584707e-7,0.0008652751,0.0008645443],"genre_scores_gemma":[0.7556158,0.0001057725,0.2431949,0.0005095747,0.000009263255,0.000002729623,8.476399e-7,0.000004237909,0.0005568736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7215537,"threshold_uncertainty_score":0.2941045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376647049085932,"score_gpt":0.2719548616959657,"score_spread":0.2581883912051063,"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."}}