{"id":"W2738173662","doi":"","title":"Semi-supervised learning and opinion-oriented information extraction","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Co-training; Classifier (UML); Graph; Semi-supervised learning; Naive Bayes classifier; Bottleneck; Information extraction; Supervised learning; Decision tree; Algorithm; Data mining; Theoretical computer science; Support vector machine","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":[0.0001139015,0.00005393883,0.00004250178,0.000107157,0.000121139,0.0001795665,0.0001570857,0.00006505297,0.0000514556],"category_scores_gemma":[0.00009551633,0.00004639956,0.0000117856,0.0001819316,0.00002728964,0.002148699,0.00009168829,0.0001861902,0.00007146012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006344011,"about_ca_system_score_gemma":0.00001279007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000879593,"about_ca_topic_score_gemma":0.000002028506,"domain_scores_codex":[0.9995716,0.000008577483,0.0001212032,0.0001040266,0.0001056334,0.00008893328],"domain_scores_gemma":[0.9996632,0.0000351905,0.00005445143,0.0001653242,0.00005200775,0.00002976765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002008315,0.00001385449,0.005250959,0.000006689931,0.000003034509,1.148965e-7,0.0003506065,0.000003182121,0.01687485,0.4828302,0.0009983011,0.4936662],"study_design_scores_gemma":[0.000493858,0.00007432138,0.02386423,0.000006485955,0.000001727537,0.00002115984,0.0007594135,0.1255183,0.02189467,0.004161613,0.8229613,0.0002429845],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06544106,0.0000142837,0.9186647,0.002941466,0.0006094978,0.0001068149,2.186271e-7,0.001256882,0.01096506],"genre_scores_gemma":[0.9631591,0.00004295166,0.03627465,0.00008094224,0.00001728172,0.00001189926,0.000006591184,0.000001681208,0.0004048514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8977181,"threshold_uncertainty_score":0.1892119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008705654857859608,"score_gpt":0.260067979323589,"score_spread":0.2513623244657294,"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."}}