{"id":"W4223491992","doi":"10.18653/v1/2022.bionlp-1.2","title":"A sequence-to-sequence approach for document-level relation extraction","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University Health Network; Vector Institute; University of Toronto","funders":"National Institutes of Health; Compute Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Pipeline (software); Coreference; Relationship extraction; Sequence (biology); Task (project management); Sentence; Relation (database); Information extraction; Natural language processing; Code (set theory); Information retrieval; Artificial intelligence; Named-entity recognition; Data mining; Resolution (logic); Programming language; Set (abstract data type)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002090993,0.003051314,0.001285746,0.005415736,0.001155113,0.001586893,0.002194527,0.002023373,0.01088727],"category_scores_gemma":[0.005348822,0.00110516,0.002575161,0.005007682,0.0006549359,0.004502529,0.002709861,0.003155846,0.01520391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053718,"about_ca_system_score_gemma":0.002970459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007126076,"about_ca_topic_score_gemma":0.01819321,"domain_scores_codex":[0.9979995,0.0003540422,0.0001767879,0.0009732856,0.0003832101,0.0001132058],"domain_scores_gemma":[0.9967577,0.001202964,0.0002388982,0.000823675,0.0008371975,0.0001395268],"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":[0.0003984807,0.00043914,0.002422998,0.0009043445,0.0002775772,0.0005244885,0.0005741406,0.01733137,0.04888942,0.01493767,0.08740827,0.8258922],"study_design_scores_gemma":[0.0001129982,0.0004619924,0.003639599,0.0001761823,0.0002916074,0.001712502,0.0003789223,0.6750948,0.05868371,0.07637356,0.1828803,0.0001939211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003757854,0.0008522291,0.9603356,0.0003313631,0.0002061453,0.0004205214,0.006030912,0.02576833,0.002297204],"genre_scores_gemma":[0.03337627,0.0006182431,0.9299126,0.0003130208,0.0001938424,0.0004915309,0.02640117,0.001112535,0.007580804],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01088727,"threshold_uncertainty_score":0.03642154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1379671748302291,"score_gpt":0.3269344450011883,"score_spread":0.1889672701709593,"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."}}