{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001080713,0.0005609548,0.0005713157,0.007419957,0.001193237,0.001962298,0.0007106588,0.0005793743,0.004733637],"category_scores_gemma":[0.009572839,0.0003350152,0.0008550427,0.003083877,0.000864003,0.003234957,0.001948592,0.0004472833,0.002237852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005098546,"about_ca_system_score_gemma":0.001014575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005118073,"about_ca_topic_score_gemma":0.006645817,"domain_scores_codex":[0.9987859,0.0002284587,0.0002136411,0.0003643313,0.0003210438,0.00008666188],"domain_scores_gemma":[0.9967247,0.001128795,0.0003909451,0.0006508509,0.0009801021,0.000124716],"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":[0.0007242381,0.0001971981,0.1331675,0.000698928,0.0003069871,0.0009402709,0.002784086,0.00356545,0.07454192,0.0314569,0.004607179,0.7470093],"study_design_scores_gemma":[0.0001546607,0.0008512295,0.2769777,0.000599362,0.00137482,0.01046727,0.008664816,0.2621492,0.1838755,0.1414186,0.1128814,0.0005853108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4927079,0.001845408,0.4673694,0.000331895,0.0001651699,0.000311671,0.002846978,0.003353148,0.03106831],"genre_scores_gemma":[0.7816811,0.0004323353,0.2107786,0.00008145212,0.00006784997,0.0001866518,0.003087714,0.0002934723,0.003390925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007419957,"threshold_uncertainty_score":0.01583552,"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."}}