{"id":"W2891886878","doi":"10.23889/ijpds.v3i4.760","title":"Learning Unsupervised Representations from Biomedical Text","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Computer science; Topic model; Natural language processing; Word2vec; Information retrieval; Statistical model; Artificial intelligence; Data science; Embedding","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.003099717,0.00007274134,0.00009840493,0.0003882178,0.002017635,0.0007124926,0.001991106,0.00004043614,0.0008466593],"category_scores_gemma":[0.005393749,0.00006758476,0.00006195738,0.0007359479,0.0007172925,0.002160828,0.0002698782,0.0001420376,0.00005394627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001536728,"about_ca_system_score_gemma":0.0004138635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003289974,"about_ca_topic_score_gemma":0.0007974424,"domain_scores_codex":[0.9972408,0.0001697019,0.0003770687,0.0003785738,0.001604491,0.0002293282],"domain_scores_gemma":[0.9974769,0.000524929,0.0002353174,0.0002213055,0.001334019,0.0002075565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001519303,0.0002620847,0.1389899,0.000002024459,0.0002428771,0.00001310804,0.01062772,0.001022616,0.003657668,0.1075476,0.01153628,0.7259461],"study_design_scores_gemma":[0.0008502248,0.00009516009,0.1935675,0.00004453877,0.00005917466,0.00001492292,0.003330221,0.1832568,0.00008406168,0.07878734,0.5396039,0.0003060558],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4600462,0.00005562044,0.5043129,0.01716383,0.01123614,0.0003034715,0.000325154,0.0001349683,0.006421715],"genre_scores_gemma":[0.9431577,0.0000298729,0.05159176,0.0001996247,0.003631551,0.000003278398,0.0006219808,0.000006149135,0.0007580604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7256401,"threshold_uncertainty_score":0.9992816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1343517857801681,"score_gpt":0.511399824377993,"score_spread":0.377048038597825,"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."}}