{"id":"W2950851846","doi":"10.18653/v1/n19-1323","title":"Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relation (database); Computer science; Relationship extraction; Computational linguistics; Artificial intelligence; Natural language processing; Association (psychology); Artificial neural network; Linguistics; Volume (thermodynamics); Knowledge extraction; Cognitive science; Information extraction; Psychology; Epistemology; Philosophy; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001539856,0.0001250228,0.0001357866,0.0000846622,0.00009591855,0.0002016857,0.0002036402,0.0001076682,0.00000437852],"category_scores_gemma":[0.00004317566,0.0001107221,0.00004026594,0.00004969702,0.000006935733,0.00023835,0.0003286291,0.0001965062,0.000004149713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003670117,"about_ca_system_score_gemma":0.00004966933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001221233,"about_ca_topic_score_gemma":0.0001504375,"domain_scores_codex":[0.9990255,0.00004057742,0.0001791879,0.0005350399,0.00008809488,0.0001315715],"domain_scores_gemma":[0.9990124,0.0002135832,0.0001386487,0.0005152507,0.00008335111,0.00003682754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003467487,0.0000656577,0.001997763,0.0004325639,0.00009869929,0.00001309429,0.0165977,0.8204594,0.00125723,0.01632952,0.00008991484,0.1426237],"study_design_scores_gemma":[0.0002822395,0.00003312835,0.0003943879,0.00003772711,0.00001413117,0.00005435935,0.0001959387,0.9973892,0.000649328,0.0007278738,0.00007382432,0.0001478613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3180632,0.0001750228,0.6796057,0.0001767406,0.0003736944,0.0004146165,0.000001849482,0.0001400305,0.001049135],"genre_scores_gemma":[0.8805362,0.000003978995,0.1187398,0.00002475855,0.00009856399,0.00004138566,0.00001665857,0.00001186612,0.0005267562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5624729,"threshold_uncertainty_score":0.4515118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04272856396996166,"score_gpt":0.3311605949007924,"score_spread":0.2884320309308308,"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."}}