{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005058942,0.00008224148,0.0000781808,0.0001021903,0.0003070404,0.00009349651,0.0005581417,0.00002494104,0.00004973367],"category_scores_gemma":[0.00003435352,0.00008484272,0.00004291557,0.0003028751,0.000007233722,0.0006249716,0.0002418185,0.0001225146,0.00001141589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002381377,"about_ca_system_score_gemma":0.00007684996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009832491,"about_ca_topic_score_gemma":0.00000275451,"domain_scores_codex":[0.9987925,0.00004955034,0.0001945831,0.0004376222,0.0003147051,0.0002110532],"domain_scores_gemma":[0.9994003,0.00005258918,0.00006379566,0.0003737093,0.0000465235,0.00006313392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001885966,0.00007742237,0.0001740125,0.00002081327,0.00001264661,0.00000398439,0.001562606,0.2309698,0.01649585,0.6440572,0.001227504,0.1053793],"study_design_scores_gemma":[0.0002571309,0.00007268626,0.0001449985,0.000001861873,0.000002800593,0.00003201523,0.0001035383,0.9796457,0.0007261272,0.01411198,0.004753651,0.0001475279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005976992,0.000008796147,0.9879968,0.001233355,0.0003018223,0.0004725842,0.000004458254,0.000178111,0.003827037],"genre_scores_gemma":[0.4845893,5.324646e-7,0.5125433,0.0003762589,0.00003408093,0.0002670823,0.00000806255,0.000004431896,0.002176932],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7486758,"threshold_uncertainty_score":0.3459786,"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."}}