{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00167655,0.001147828,0.0008047551,0.002812313,0.0005707635,0.001884736,0.001938388,0.00158123,0.005652067],"category_scores_gemma":[0.008957567,0.0004197147,0.001296428,0.003234476,0.0008497179,0.002352682,0.00151528,0.001905014,0.003492243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001214504,"about_ca_system_score_gemma":0.001441375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005075152,"about_ca_topic_score_gemma":0.005333394,"domain_scores_codex":[0.9986357,0.0003526596,0.00009867515,0.0005542142,0.0002340313,0.0001246415],"domain_scores_gemma":[0.9956404,0.002698529,0.000325053,0.0006593929,0.0005641939,0.0001122995],"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":[0.0003457869,0.0003751343,0.004620209,0.0005342555,0.0002064706,0.0003663822,0.0002668763,0.182199,0.006016827,0.01338113,0.05875916,0.7329288],"study_design_scores_gemma":[0.00003020593,0.00006320199,0.001200861,0.00007290172,0.00003505871,0.0001264126,0.00007998849,0.9629088,0.00311973,0.02355883,0.008778397,0.00002568749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06100664,0.003345552,0.9002513,0.003113722,0.0006727071,0.0003559696,0.01076373,0.01283283,0.007657583],"genre_scores_gemma":[0.5631311,0.002920233,0.3554221,0.001313696,0.001672701,0.0009335864,0.05574753,0.0007024569,0.01815663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005652067,"threshold_uncertainty_score":0.01890808,"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."}}