{"id":"W2250974997","doi":"10.63317/29jpe4q7e5co","title":"Improving Open Relation Extraction via Sentence Re-Structuring","year":2014,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Relationship extraction; Structuring; Natural language processing; Information extraction; Artificial intelligence; Predicate (mathematical logic); Sentence; Natural language; Open domain; Exploit; Natural language understanding; Relation (database); Context (archaeology); Information retrieval; Data mining; Question answering; Programming language","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":[0.0003681607,0.00006418639,0.00006564983,0.00004120884,0.0001345447,0.0002554171,0.0006760204,0.00003815338,0.00002335476],"category_scores_gemma":[0.00005406897,0.00005923385,0.00001752264,0.00009171396,0.000006776549,0.001534997,0.0003957076,0.00009635361,0.00003246347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003865278,"about_ca_system_score_gemma":0.00001414662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004604344,"about_ca_topic_score_gemma":0.00004042023,"domain_scores_codex":[0.9992169,0.00003765255,0.0001601357,0.0003075288,0.0001388486,0.000138983],"domain_scores_gemma":[0.9993525,0.00004300726,0.00008170377,0.0004462205,0.00003426507,0.00004227299],"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":[0.000002524414,0.000008815875,0.001283922,0.00001123305,0.00000329147,0.000001686499,0.0003305189,0.004880804,0.03379196,0.07244096,0.00005054542,0.8871937],"study_design_scores_gemma":[0.0001036178,0.00001145087,0.002970008,0.000007580004,0.000001221156,0.00001106644,0.00001289042,0.9820593,0.006114871,0.008224313,0.0003972098,0.0000864413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02486248,0.000003468098,0.9629448,0.000431029,0.0003987386,0.0001034153,2.87375e-8,0.0001397589,0.01111628],"genre_scores_gemma":[0.7013391,4.225135e-7,0.2980732,0.0001530027,0.00005985089,0.000002992665,3.062832e-7,0.000003124054,0.0003680412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9771785,"threshold_uncertainty_score":0.2462993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02503818307054018,"score_gpt":0.2652567600072647,"score_spread":0.2402185769367245,"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."}}