{"id":"W2584524946","doi":"10.1109/bigdata.2016.7841060","title":"Efficient natural language pre-processing for analyzing large data sets","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; WordNet; Pipeline (software); Natural language processing; Machine translation; Preprocessor; Task (project management); Graph; Variety (cybernetics); Machine learning","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":[0.0004140766,0.00008319467,0.0000920606,0.0000520352,0.0001043964,0.0001087822,0.001255474,0.00002751167,0.00001076335],"category_scores_gemma":[0.00009537037,0.00004982211,0.00002714097,0.0001133556,0.000009195062,0.0003109935,0.0007116277,0.00004262228,0.00001141149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002494479,"about_ca_system_score_gemma":0.00004083208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001081842,"about_ca_topic_score_gemma":0.00002237735,"domain_scores_codex":[0.9989244,0.00001578188,0.0001477285,0.0004574023,0.000153524,0.0003011803],"domain_scores_gemma":[0.9988351,0.00008396032,0.0000479874,0.0009423044,0.00004194775,0.00004871186],"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":[0.000005953079,0.00004435424,0.0004709713,0.00004357518,0.00001379877,0.000006224455,0.001344595,0.0002738171,0.006113338,0.01051104,0.0008829141,0.9802894],"study_design_scores_gemma":[0.0003219641,0.000006267591,0.0002225544,0.00003628138,0.00000344619,0.000003324646,0.00002731971,0.9974481,0.0008494668,0.0001256205,0.0008486619,0.0001069379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05735998,0.0005279887,0.9405951,0.0007912057,0.0002151138,0.0001103739,0.00001223015,0.0001786933,0.0002093017],"genre_scores_gemma":[0.8239678,6.823911e-7,0.1751816,0.0001657595,0.00006413092,0.000003809572,0.00000441501,0.000005303471,0.0006065039],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9971743,"threshold_uncertainty_score":0.2333004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02934926712142034,"score_gpt":0.3177701427171664,"score_spread":0.2884208755957461,"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."}}