{"id":"W2039427737","doi":"10.3115/1220575.1220583","title":"Redundancy-based correction of automatically extracted facts","year":2005,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Redundancy (engineering); Pipeline (software); Computer science; Information extraction; Data mining; Event (particle physics); Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00367538,0.001487612,0.001277556,0.005119737,0.0008583353,0.001284498,0.00179104,0.0009409254,0.002526687],"category_scores_gemma":[0.02743686,0.0006132062,0.0009181669,0.002939944,0.0007476852,0.002751686,0.001498892,0.001268794,0.001913464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005736082,"about_ca_system_score_gemma":0.001474525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002695794,"about_ca_topic_score_gemma":0.004204972,"domain_scores_codex":[0.9964563,0.0007221379,0.0003316402,0.0008125101,0.00149839,0.0001789519],"domain_scores_gemma":[0.9696595,0.01265957,0.003186615,0.008963727,0.005370945,0.0001594692],"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":[0.0007120101,0.0001363508,0.01212815,0.0009618124,0.0002709697,0.001529734,0.00113427,0.02333754,0.07950704,0.005404036,0.01573494,0.8591432],"study_design_scores_gemma":[0.000111557,0.0005025513,0.02291369,0.0003066374,0.0008458979,0.003894219,0.0004968329,0.4548041,0.427542,0.02355841,0.06478304,0.0002410819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1236594,0.001506147,0.8429934,0.00079787,0.0003566598,0.0003255794,0.002449944,0.02440553,0.003505448],"genre_scores_gemma":[0.3721597,0.0006468151,0.6142814,0.0002727752,0.0002484062,0.0001422121,0.005227491,0.001609047,0.005412257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005119737,"threshold_uncertainty_score":0.01943755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009424979568080563,"score_gpt":0.2671534743695565,"score_spread":0.2577284948014759,"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."}}