{"id":"W3116628494","doi":"10.18653/v1/2020.coling-tutorials.7","title":"Endangered Languages meet Modern NLP","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"University of Notre Dame; Carleton University; Carnegie Mellon University","keywords":"Computer science; Natural language processing; Endangered species; Artificial intelligence; Biology; Ecology","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":[0.00006394987,0.00009660069,0.0001037424,0.00003274365,0.00004114138,0.0001353181,0.0009115094,0.00004627564,0.00004002345],"category_scores_gemma":[0.0000695578,0.00007533305,0.00003659482,0.0002400802,0.00001651664,0.0003839665,0.000309962,0.0000903893,0.00004354606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000131143,"about_ca_system_score_gemma":0.000023636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002126366,"about_ca_topic_score_gemma":0.00000573766,"domain_scores_codex":[0.9992422,0.00002182258,0.0001013886,0.0002836001,0.0001809034,0.0001700625],"domain_scores_gemma":[0.9995305,0.00002607732,0.00003442202,0.0002723196,0.0000385414,0.00009813483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009887357,0.00004411891,0.0001781285,0.00006926402,0.00002464812,0.0002096961,0.007996687,0.000007095592,0.1069712,0.4187573,0.04492026,0.4208116],"study_design_scores_gemma":[0.000381311,0.0001717305,0.00006978332,0.00003117718,0.000009204535,0.00003927464,0.0001159816,0.1532552,0.7141765,0.1227395,0.008318225,0.0006920786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005574969,0.002008726,0.9758062,0.01003338,0.0000324775,0.0000747439,0.000001450282,0.002300377,0.00918515],"genre_scores_gemma":[0.4999712,0.00000316998,0.4960226,0.003738446,0.00005066478,0.000003875499,9.278507e-7,0.000005711945,0.000203405],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6072053,"threshold_uncertainty_score":0.3071993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01814678136304938,"score_gpt":0.270956021396855,"score_spread":0.2528092400338056,"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."}}