{"id":"W2003185534","doi":"10.3115/1572340.1572361","title":"Syntactic dependency based heuristics for biological event extraction","year":2009,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Negation; Heuristics; Parsing; Dependency (UML); Biomedical text mining; Task (project management); Syntax; Dependency grammar; Event (particle physics); Natural language processing; Artificial intelligence; Programming language; Text mining","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":[0.0001478718,0.00009964021,0.00009845759,0.00001976311,0.00006300298,0.0000119019,0.0001029989,0.0002169296,0.00004852247],"category_scores_gemma":[0.0004698136,0.00007388234,0.00008817937,0.00003186473,0.00004068404,0.000001009249,0.00001232637,0.00006016343,0.000009141506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009281253,"about_ca_system_score_gemma":0.00003981781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002718401,"about_ca_topic_score_gemma":0.000003314101,"domain_scores_codex":[0.9993172,0.0000275731,0.0001474406,0.0002437439,0.00007106789,0.0001929969],"domain_scores_gemma":[0.9996335,0.00005023833,0.00004444968,0.0001603844,0.00004451138,0.00006691558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005576602,0.0006595858,0.002290757,0.0000259154,0.000048366,0.00001197622,0.00001051672,0.00005367571,0.565532,0.001171903,0.01735106,0.4122866],"study_design_scores_gemma":[0.003157727,0.01010841,0.04651205,0.00004210553,0.00009071596,0.00009946148,0.0002119094,0.00483143,0.4358896,0.007023498,0.4909705,0.001062532],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.262739,0.0005347318,0.7321164,0.002130714,0.0003387173,0.0002706333,0.00001675479,0.00008811963,0.001764901],"genre_scores_gemma":[0.9759497,0.00004664523,0.02241807,0.0008814483,0.0001768115,0.00001537695,0.00007917821,0.000004936459,0.0004278179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7132107,"threshold_uncertainty_score":0.3012834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048695666431839,"score_gpt":0.3342910224198971,"score_spread":0.3038040657555787,"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."}}