{"id":"W1518614801","doi":"","title":"Identification of Cognates and Recurrent Sound Correspondences in Word Lists","year":2009,"lang":"fr","type":"article","venue":"Trait. Autom. des Langues","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Natural language processing; Computer science; Similarity (geometry); Artificial intelligence; Identification (biology); Recall; Cognate; Linguistics; Speech recognition","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":[0.0007669828,0.0002370528,0.0003275757,0.000301856,0.00008369903,0.0003158142,0.0006410209,0.0001732897,0.00002460564],"category_scores_gemma":[0.0003103848,0.0002256361,0.00005692359,0.0007427192,0.0004451093,0.0009403708,0.00009487963,0.0002727081,0.000008356946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007611873,"about_ca_system_score_gemma":0.00007813331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003338837,"about_ca_topic_score_gemma":0.0003318367,"domain_scores_codex":[0.9980848,0.0001879932,0.0005598509,0.0004713866,0.0003285425,0.0003674186],"domain_scores_gemma":[0.998921,0.0002109476,0.0002994724,0.0003054756,0.0001788265,0.00008421678],"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":[0.00004730573,0.0002191909,0.001108742,0.000265465,0.00001204807,0.00005890223,0.01533535,0.000005114903,0.01361167,0.02848014,0.0003687781,0.9404873],"study_design_scores_gemma":[0.0009622088,0.0009505373,0.2526909,0.004247603,0.00009531617,0.0002474782,0.0008198964,0.04116222,0.08851872,0.6083395,0.0007476002,0.001217955],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7742407,0.1986717,0.02363901,0.001814134,0.0006178885,0.0003502156,0.00003762375,0.0004321455,0.0001965729],"genre_scores_gemma":[0.9481373,0.0006071842,0.05007187,0.0001096576,0.00007259264,0.000008075023,0.000009013532,0.0000102987,0.0009739744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9392694,"threshold_uncertainty_score":0.9201171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02855780058389824,"score_gpt":0.3165577630512376,"score_spread":0.2879999624673393,"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."}}