{"id":"W2129123581","doi":"10.3115/1641976.1641983","title":"Evaluation of several phonetic similarity algorithms on the task of cognate identification","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Similarity (geometry); Context (archaeology); Hidden Markov model; Identification (biology); Task (project management); Artificial intelligence; Set (abstract data type); Cognate; Cluster analysis; Natural language processing; Speech recognition; Pattern recognition (psychology); Image (mathematics); Linguistics","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":[0.001988442,0.0000622092,0.00007824503,0.00006213865,0.00004423249,0.00003479562,0.0004897513,0.00003923117,0.00002069259],"category_scores_gemma":[0.0001264474,0.00004043345,0.00003203146,0.0002910095,0.00003172251,0.0001679676,0.00007328764,0.00007155127,0.00000412861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003441181,"about_ca_system_score_gemma":0.00005328613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001421095,"about_ca_topic_score_gemma":0.000009583325,"domain_scores_codex":[0.9986194,0.000153095,0.0002298079,0.0001625667,0.0007472422,0.00008792581],"domain_scores_gemma":[0.9987977,0.00008098918,0.0001849676,0.0003723635,0.0005551913,0.000008809929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001892157,0.0006191946,0.0001592136,0.00008958241,0.00005100184,0.000001944822,0.001132107,0.004535238,0.3048135,0.4290618,0.007757689,0.2517598],"study_design_scores_gemma":[0.00009115147,0.00002348417,0.00205469,0.00001653905,0.00001435549,0.000001013669,0.000005340261,0.4541769,0.4101616,0.1333964,0.000009992075,0.00004846835],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02409403,0.0003429962,0.9732727,0.0007444345,0.00009367688,0.0002661987,0.000003252048,0.0001161947,0.001066463],"genre_scores_gemma":[0.9386579,0.000001702058,0.06114906,0.00006508455,0.00001359613,0.00001064597,0.000003441243,0.000002747014,0.00009578959],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9145639,"threshold_uncertainty_score":0.1648828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02583546049157253,"score_gpt":0.2935216319955214,"score_spread":0.2676861715039489,"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."}}