{"id":"W2923261428","doi":"10.48550/arxiv.1903.10126","title":"Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Computer science; Relation (database); Code (set theory); Natural language processing; Relationship extraction; Artificial intelligence; Constant (computer programming); Data science; Programming language; Data mining; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001221935,0.001056544,0.0007323795,0.002276287,0.0005795314,0.001921865,0.002184566,0.001851394,0.006561955],"category_scores_gemma":[0.008699056,0.000816954,0.001733223,0.003182066,0.0007680785,0.006681038,0.002629646,0.00310049,0.002698583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001245101,"about_ca_system_score_gemma":0.000791046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005459192,"about_ca_topic_score_gemma":0.01127208,"domain_scores_codex":[0.999246,0.0002584792,0.000050041,0.0002773108,0.0000939103,0.00007437835],"domain_scores_gemma":[0.9976667,0.001457187,0.0001505757,0.0004494512,0.0001937671,0.0000823771],"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":[0.000313634,0.0003175696,0.003931465,0.000394236,0.0003630617,0.0003488663,0.0006012528,0.2156817,0.00617873,0.06490386,0.02295208,0.6840135],"study_design_scores_gemma":[0.00001688571,0.0000295001,0.0004572797,0.00005705621,0.00005451517,0.00008626206,0.00007821317,0.8614994,0.001592447,0.1321247,0.003983092,0.00002063095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03778127,0.00211248,0.9479966,0.002040322,0.0001836928,0.00009399725,0.001597421,0.003545939,0.004648404],"genre_scores_gemma":[0.6737883,0.00215214,0.3023748,0.0009635485,0.0004595009,0.0004020307,0.007231899,0.000580004,0.01204777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006561955,"threshold_uncertainty_score":0.02195197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0808915080268491,"score_gpt":0.2369188515485596,"score_spread":0.1560273435217105,"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."}}