{"id":"W2027097848","doi":"10.3115/1626516.1626533","title":"Creating a comparative dictionary of Totonac-Tepehua","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Wenner-Gren Foundation","keywords":"Cognate; Computer science; Language family; Identification (biology); Natural language processing; Artificial intelligence; Indigenous; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003628256,0.0003086737,0.0004022458,0.002878452,0.001316248,0.0008162378,0.0005399272,0.0002613179,0.007231969],"category_scores_gemma":[0.002257894,0.0002182414,0.0002086625,0.002388739,0.0007241915,0.0011973,0.001054454,0.0005425548,0.001244993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005524931,"about_ca_system_score_gemma":0.001385892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004086193,"about_ca_topic_score_gemma":0.01061857,"domain_scores_codex":[0.9996674,0.00004744012,0.00004532626,0.0001439329,0.00007280283,0.00002318236],"domain_scores_gemma":[0.9992719,0.0001869201,0.00005852551,0.0001924683,0.0002526253,0.00003751642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"design_other","study_design_scores_codex":[0.0004114343,0.0001472022,0.01611669,0.0009528559,0.00006891033,0.002570158,0.009808673,0.003534395,0.05612048,0.09175759,0.0165927,0.8019189],"study_design_scores_gemma":[0.000102861,0.0004515034,0.07180825,0.0007028253,0.0002107306,0.0105078,0.01490708,0.04083273,0.03637883,0.04517128,0.7787322,0.0001939402],"study_design_candidate":"design_other","study_design_consensus":"design_other","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5297554,0.001520845,0.3556379,0.0005506243,0.0005879555,0.0005986856,0.01347467,0.002310822,0.09556309],"genre_scores_gemma":[0.6097006,0.0007771294,0.3666257,0.00008591908,0.00005454536,0.0003636163,0.01304216,0.0005967608,0.008753491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007231969,"threshold_uncertainty_score":0.02419341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02095664878535249,"score_gpt":0.3178112487715095,"score_spread":0.296854599986157,"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."}}