{"id":"W2951890879","doi":"10.48550/arxiv.1906.11483","title":"Morphological Irregularity Correlates with Frequency","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Predictability; Correlation; Computer science; Measure (data warehouse); Code (set theory); Natural language processing; Artificial intelligence; Linguistics; Mathematics; Statistics; Data mining","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":[0.0009386891,0.0002444492,0.0003529091,0.002787566,0.000510719,0.001188029,0.0004243889,0.0004336255,0.004748908],"category_scores_gemma":[0.01783418,0.0002320968,0.0003804827,0.002951159,0.001352459,0.001988362,0.001256074,0.0008291237,0.0008830127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002419817,"about_ca_system_score_gemma":0.0001969036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004938911,"about_ca_topic_score_gemma":0.0004587664,"domain_scores_codex":[0.9992697,0.0001666977,0.00007788867,0.0002208476,0.0001981138,0.00006679494],"domain_scores_gemma":[0.9787011,0.01062539,0.005146509,0.003597016,0.00149133,0.0004385614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006554331,0.0001493216,0.7647668,0.0002325542,0.0002739503,0.0008891968,0.003062977,0.006357421,0.0401903,0.02876552,0.001372513,0.153284],"study_design_scores_gemma":[0.00001773746,0.0002225854,0.8603729,0.00003776713,0.0001210209,0.003639934,0.0009584545,0.03501774,0.009194585,0.08510881,0.005214385,0.00009412937],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.980199,0.0002471383,0.0148406,0.0001416208,0.00001057247,0.000009117321,0.0003048174,0.0001063037,0.004140808],"genre_scores_gemma":[0.996874,0.00008612213,0.002294423,0.00001518881,0.00001867204,0.000006420224,0.0002580142,0.00004752135,0.0003996908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004748908,"threshold_uncertainty_score":0.01588666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04140141533401594,"score_gpt":0.1879616409647252,"score_spread":0.1465602256307093,"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."}}