{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002873845,0.002443388,0.001763074,0.006129188,0.001673164,0.00287137,0.001849284,0.001065364,0.006662247],"category_scores_gemma":[0.01169153,0.001085983,0.002622415,0.005050937,0.00137392,0.003867833,0.002434404,0.003024009,0.01128066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001052513,"about_ca_system_score_gemma":0.002670316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003001411,"about_ca_topic_score_gemma":0.004739769,"domain_scores_codex":[0.9972931,0.0007293119,0.0003460462,0.0006320191,0.0008621854,0.0001373307],"domain_scores_gemma":[0.9889073,0.006757912,0.000828155,0.001631706,0.001718919,0.0001560164],"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":[0.0002733251,0.0003355038,0.002410808,0.001877736,0.0001728166,0.0007644268,0.0007767529,0.01101402,0.09251669,0.01162857,0.022108,0.8561212],"study_design_scores_gemma":[0.0001225364,0.0006662197,0.01504008,0.000450429,0.0003067654,0.002055424,0.002698062,0.5985909,0.1236827,0.1362225,0.1198564,0.0003080257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006971184,0.0006150529,0.9748504,0.0004995855,0.0001241712,0.0008209222,0.00296671,0.01179843,0.001353601],"genre_scores_gemma":[0.03113639,0.0006956861,0.9557526,0.0002251617,0.0001873226,0.001535594,0.008723563,0.0005030804,0.00124058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006662247,"threshold_uncertainty_score":0.02228743,"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."}}