{"id":"W2397269111","doi":"","title":"Generalizing from Freebase and Patterns using Cluster-Based Distant Supervision for TAC KBP Slotfilling 2012.","year":2012,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Sentence; Classifier (UML); Word (group theory); Training set; Set (abstract data type); Natural language processing; Test set; Artificial intelligence; Information retrieval; Context (archaeology); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004699188,0.0001062778,0.0001309901,0.00005973935,0.0002124291,0.00007567988,0.0002351644,0.00005049217,0.000003309553],"category_scores_gemma":[0.00002392103,0.00008918245,0.00002421673,0.0001009036,0.00009358092,0.0006326272,0.0001205247,0.00005548367,1.989794e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001036032,"about_ca_system_score_gemma":0.00001694597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006540936,"about_ca_topic_score_gemma":0.000003410222,"domain_scores_codex":[0.9993495,0.00005310665,0.0001687182,0.0001954165,0.0000782941,0.0001549731],"domain_scores_gemma":[0.9991533,0.0003157822,0.00009796044,0.0003048573,0.00006835983,0.00005976326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003270797,0.00004665689,0.0008504891,0.0001233555,0.00001042757,1.260621e-7,0.001088561,0.00001475378,0.03925923,0.9187584,0.00001520619,0.0398001],"study_design_scores_gemma":[0.0003503841,0.00004754178,0.0001190348,0.00008346612,0.00005130381,0.000004359124,0.000315219,0.01524095,0.3291932,0.6530928,0.00120099,0.0003007915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1599236,0.006416751,0.8331901,0.00009281334,0.0000276563,0.0002175427,0.00004091245,0.00008331901,0.000007306622],"genre_scores_gemma":[0.7321861,0.00003014101,0.2675432,0.00007498821,0.00006952579,0.00005769154,0.00002444687,0.000007558938,0.000006298613],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5722625,"threshold_uncertainty_score":0.3636754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01750765833137411,"score_gpt":0.2808672439289689,"score_spread":0.2633595855975948,"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."}}