{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001071981,0.0005038293,0.0006254069,0.009206038,0.001238361,0.002254683,0.0009384454,0.001084131,0.00395832],"category_scores_gemma":[0.0082218,0.0004607398,0.0005348256,0.003232273,0.0008826845,0.004403337,0.00147547,0.0005848545,0.002468554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005344763,"about_ca_system_score_gemma":0.0008953072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002875328,"about_ca_topic_score_gemma":0.005124371,"domain_scores_codex":[0.998594,0.0002574674,0.0002055613,0.0005279325,0.0002981927,0.0001168352],"domain_scores_gemma":[0.9944761,0.002298991,0.0009596906,0.000996942,0.001094843,0.0001734293],"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":[0.0006788013,0.00027713,0.05760707,0.000590859,0.0001696296,0.0008306733,0.002955865,0.004502563,0.07073329,0.01810219,0.004507136,0.8390448],"study_design_scores_gemma":[0.0001983472,0.0008598904,0.1499379,0.0003743322,0.000706495,0.007137578,0.008993874,0.4636053,0.1927684,0.1251024,0.04984912,0.0004663265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5281326,0.0008171435,0.4532658,0.000265281,0.00007970418,0.0002919598,0.002235882,0.005850439,0.009061164],"genre_scores_gemma":[0.750185,0.0003095987,0.2421008,0.00005462574,0.0000703918,0.0001279323,0.003592341,0.0002615358,0.003297791],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.009206038,"threshold_uncertainty_score":0.01324189,"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."}}