{"id":"W3029889931","doi":"","title":"The Johns Hopkins University Bible Corpus: 1600+ Tongues for Typological Exploration","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Natural language processing; Variety (cybernetics); Representation (politics); Linguistics; Corpus linguistics; Parallel corpora; Pronoun; Artificial intelligence; Information retrieval; History; Machine translation; Philosophy","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":[0.0004986699,0.00007298298,0.000073808,0.00007073188,0.0002955648,0.000187172,0.0003048732,0.00005245047,0.000005249361],"category_scores_gemma":[0.0002518368,0.00004942688,0.00002971688,0.0004232268,0.00004152854,0.000343565,0.000114852,0.00007105064,0.00000277441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002365186,"about_ca_system_score_gemma":0.00002247071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008821391,"about_ca_topic_score_gemma":0.00006377166,"domain_scores_codex":[0.9992493,0.0001105396,0.00008782236,0.0002146638,0.0002137881,0.0001238394],"domain_scores_gemma":[0.9994751,0.0001537829,0.00007571391,0.0001433523,0.000102771,0.00004924864],"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":[0.0001133562,0.00002330898,0.0001974206,0.00004862422,0.00002092335,0.00000850193,0.02768186,0.00007008603,0.003805647,0.02990418,0.00199516,0.9361309],"study_design_scores_gemma":[0.001316364,0.0007640754,0.0008876045,0.0000627971,0.00008872807,0.0000122799,0.007898438,0.7067691,0.01441784,0.01234176,0.2549401,0.0005009186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2157518,0.008942667,0.7533713,0.01834793,0.0001409525,0.001057734,0.0000112756,0.0007873097,0.001589084],"genre_scores_gemma":[0.9414427,0.0009410963,0.05680626,0.0005364575,0.0001762225,0.00001516812,0.00001892144,0.000007006536,0.00005620984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.93563,"threshold_uncertainty_score":0.2273275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04572153790965464,"score_gpt":0.2934511416866595,"score_spread":0.2477296037770049,"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."}}