{"id":"W26197850","doi":"10.1007/s10654-015-0070-1","title":"Relation extraction from biomedical text","year":2007,"lang":"en","type":"dissertation","venue":"European Journal of Epidemiology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Relationship extraction; Discriminative model; Artificial intelligence; Parsing; Generative grammar; Natural language processing; Generative model; Machine learning; Information extraction; Biomedical text mining; Sentence; Boosting (machine learning); Information retrieval; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001505728,0.002189078,0.0009797427,0.01349248,0.0009595539,0.001987519,0.001289485,0.001248906,0.008376745],"category_scores_gemma":[0.01138411,0.0005721817,0.001682633,0.008932634,0.0006761527,0.004569238,0.002122127,0.001231571,0.008494511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001087957,"about_ca_system_score_gemma":0.001929908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002546042,"about_ca_topic_score_gemma":0.00376565,"domain_scores_codex":[0.9972351,0.0004658669,0.0004646301,0.0009549278,0.0007731695,0.0001063133],"domain_scores_gemma":[0.9933503,0.003595789,0.001014058,0.0007644572,0.001122051,0.0001534369],"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":[0.0004313321,0.0001813649,0.006705088,0.007663978,0.0002867182,0.002918602,0.001138757,0.007993458,0.05356367,0.02086363,0.06584506,0.8324083],"study_design_scores_gemma":[0.000139606,0.0003210434,0.0269392,0.002127411,0.00101182,0.005887859,0.002121865,0.1523074,0.09658178,0.1299815,0.5822842,0.0002963573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05770964,0.01811747,0.7391647,0.004795976,0.001216521,0.001877344,0.12986,0.02185329,0.02540506],"genre_scores_gemma":[0.1471592,0.007464832,0.6556385,0.0009554373,0.000851488,0.0009342218,0.1774468,0.001209854,0.008339638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01349248,"threshold_uncertainty_score":0.028023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04590250778340296,"score_gpt":0.37262066374105,"score_spread":0.326718155957647,"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."}}