{"id":"W2964298985","doi":"","title":"Automatic Text Summarization Approaches to Speed up Topic Model Learning Process","year":2016,"lang":"en","type":"other","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Automatic summarization; Computer science; Representation (politics); Information retrieval; Process (computing); Context (archaeology); Big data; Text processing; Space (punctuation); The Internet; Natural language processing; Data science; World Wide Web; Data mining","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":[0.001585961,0.002096176,0.001446036,0.004724051,0.001048823,0.002499802,0.001473059,0.001206513,0.02881481],"category_scores_gemma":[0.007146516,0.0006878374,0.001587384,0.004559547,0.0002701127,0.003405134,0.001510662,0.00190099,0.02452832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006131033,"about_ca_system_score_gemma":0.001204516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003683063,"about_ca_topic_score_gemma":0.006830205,"domain_scores_codex":[0.998665,0.0004031634,0.0001575081,0.0003285569,0.0003495553,0.00009631785],"domain_scores_gemma":[0.9955106,0.001892432,0.000215533,0.000492753,0.001732001,0.0001567416],"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":[0.0004420897,0.000206853,0.0006033895,0.0006970268,0.0001490881,0.0001396515,0.0001842962,0.008973591,0.02412802,0.002338975,0.09413597,0.8680012],"study_design_scores_gemma":[0.0002732099,0.0004175783,0.002709007,0.0001237178,0.0005083748,0.000420182,0.0003236521,0.8036972,0.06074044,0.01447929,0.1162091,0.00009821171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01427576,0.003182691,0.9111458,0.000902486,0.001223745,0.0006213447,0.008143825,0.05329598,0.007208463],"genre_scores_gemma":[0.08589793,0.001539508,0.8491089,0.0002345386,0.0009650201,0.0006632897,0.03448911,0.002912819,0.02418889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02881481,"threshold_uncertainty_score":0.09639519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02694046449698274,"score_gpt":0.257885706605855,"score_spread":0.2309452421088722,"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."}}