{"id":"W4385893888","doi":"10.18653/v1/2023.bionlp-1.25","title":"Extracting Drug-Drug and Protein-Protein Interactions from Text using a Continuous Update of Tree-Transformers","year":2023,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Sentence; Computer science; Transformer; Artificial intelligence; Natural language processing; Tree (set theory); Mathematics","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":[0.000167593,0.0001311379,0.0001832293,0.00006288023,0.00008244812,0.00002026679,0.00009785022,0.00008706073,0.0000513269],"category_scores_gemma":[0.00009575319,0.0001112426,0.00006855541,0.000132328,0.0001562962,0.000006151729,0.00007605784,0.000118376,0.000009251235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006672152,"about_ca_system_score_gemma":0.00003935795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005935846,"about_ca_topic_score_gemma":0.0003399459,"domain_scores_codex":[0.9991003,0.00004740783,0.0002457385,0.0002852528,0.0001003791,0.0002209355],"domain_scores_gemma":[0.9996148,0.00003326079,0.00009310002,0.0001482316,0.0000404945,0.00007006141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006435069,0.00002577988,0.000504038,0.0000209722,0.00005582903,0.00000443722,0.0001404019,0.000001928262,0.9368283,0.00001675569,0.0005693798,0.06176786],"study_design_scores_gemma":[0.0007482432,0.000108539,0.001151218,0.0001531864,0.00003778633,0.00001136109,0.003507796,0.0008689593,0.965864,0.0002787524,0.02698692,0.0002832093],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952139,0.0002885319,0.00247406,0.0005400214,0.00008216069,0.0001991688,0.00003178598,0.00005244563,0.001117975],"genre_scores_gemma":[0.9916333,0.00004449492,0.005742927,0.00004982643,0.00007697882,0.00001933958,0.00006042939,0.00001591911,0.002356762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06148466,"threshold_uncertainty_score":0.4536343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01771311462866948,"score_gpt":0.2848994085851069,"score_spread":0.2671862939564374,"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."}}