{"id":"W1987756646","doi":"10.1007/s10994-009-5151-5","title":"A co-classification approach to learning from multilingual corpora","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Categorization; Artificial intelligence; Boosting (machine learning); Regularization (linguistics); Natural language processing; Benchmarking; Consistency (knowledge bases); Text categorization; Machine learning","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":[0.0004805815,0.0002053966,0.0002129102,0.000196269,0.0003094629,0.0003278538,0.0008676764,0.0001144661,0.000009719724],"category_scores_gemma":[0.0005149575,0.0001917604,0.00005686011,0.0004933618,0.00001932623,0.0003492356,0.0001043419,0.0008765738,0.00005611171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005727802,"about_ca_system_score_gemma":0.00003375792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001422861,"about_ca_topic_score_gemma":0.000002045042,"domain_scores_codex":[0.9982787,0.0002029769,0.0002491153,0.0006068752,0.000347257,0.0003150513],"domain_scores_gemma":[0.9991418,0.0001016077,0.0001854754,0.0003623346,0.00008147995,0.0001272689],"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":[0.00003969925,0.0001871108,0.009763365,0.00001652855,0.00001806347,0.00003240375,0.006913859,0.004619214,0.1098906,0.01669215,0.0003009111,0.8515261],"study_design_scores_gemma":[0.000373118,0.0002603056,0.006326989,0.00005757127,0.00000918299,0.00002158564,0.0001057911,0.9635597,0.01710908,0.005114126,0.006532614,0.0005298763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0351734,0.0007605026,0.9562909,0.000812099,0.00005969527,0.0001954334,9.956696e-7,0.002126655,0.004580319],"genre_scores_gemma":[0.6150366,0.000002621679,0.3840418,0.0003521319,0.00007186423,0.000006828438,0.00004108115,0.00001139572,0.0004356901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9589406,"threshold_uncertainty_score":0.7819762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02645328759020278,"score_gpt":0.2968939080229041,"score_spread":0.2704406204327013,"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."}}