{"id":"W2133823287","doi":"10.1016/j.jbi.2010.07.003","title":"Unsupervised grammar induction and similarity retrieval in medical language processing using the Deterministic Dynamic Associative Memory (DDAM) model","year":2010,"lang":"en","type":"review","venue":"Journal of Biomedical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Conestoga College","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Representation (politics); Grammar; Similarity (geometry); Selection (genetic algorithm); Associative property; Content-addressable memory; Unsupervised learning; Information processing; Machine learning; Information retrieval; Artificial neural network","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003889182,0.0002971954,0.001149046,0.0004682641,0.0001448375,0.0002335502,0.00110664,0.0008476569,0.000003631261],"category_scores_gemma":[0.001599722,0.0001807861,0.0002068673,0.0006642989,0.0002759796,0.000728675,0.0004321076,0.002994225,8.304456e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000329438,"about_ca_system_score_gemma":0.002306794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004787696,"about_ca_topic_score_gemma":0.000006685055,"domain_scores_codex":[0.995549,0.0002180704,0.002168201,0.0001468556,0.001571015,0.0003468592],"domain_scores_gemma":[0.9969776,0.0004250017,0.001801795,0.0003171456,0.0001752728,0.0003031803],"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":[0.000002618094,0.00003855007,6.319411e-7,0.002105325,0.00002787572,0.00006560532,0.004177941,0.00003265633,0.000001310381,0.00001967582,0.000006797651,0.993521],"study_design_scores_gemma":[0.0003398323,0.00004659867,0.000001859538,0.004799061,0.0001441946,0.001152098,0.0004424652,0.9891046,3.681833e-7,0.0003086396,0.003466166,0.0001940648],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.002656071,0.412707,0.5831696,0.0003305224,0.0007398402,0.00033475,0.000009153934,0.00002415697,0.00002888744],"genre_scores_gemma":[0.002574452,0.8660147,0.1302848,0.0005155806,0.0005386584,0.000004100726,0.00001318015,0.00003929749,0.0000152074],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.993327,"threshold_uncertainty_score":0.9993059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05273643276839589,"score_gpt":0.3650466713035312,"score_spread":0.3123102385351353,"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."}}