{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005333573,0.0008231383,0.0009088072,0.001864035,0.0002213777,0.0004048172,0.00254477,0.000750583,0.0001712634],"category_scores_gemma":[0.0002470371,0.0007458362,0.000271522,0.001234198,0.00008602745,0.0006416556,0.0007607505,0.0006503223,0.0001744663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006181498,"about_ca_system_score_gemma":0.000374263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000602094,"about_ca_topic_score_gemma":0.0007551069,"domain_scores_codex":[0.9959504,0.0001879623,0.0007144525,0.001328309,0.0007997421,0.001019147],"domain_scores_gemma":[0.9966813,0.00008573299,0.000734193,0.001962537,0.0001151485,0.000421085],"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":[0.00003241936,0.0004576981,0.003158296,0.0006935251,0.0004366308,0.00006927548,0.001521964,0.04192059,0.002093306,0.2628379,0.1295789,0.5571995],"study_design_scores_gemma":[0.000255669,0.00007908684,0.0001014748,0.0004243359,0.00005554884,0.00001921105,0.0000211443,0.9665728,0.002979803,0.01248893,0.01594345,0.001058504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001113336,0.0003673597,0.9450365,0.001888504,0.0001050059,0.001465665,0.00001529417,0.006948891,0.04406143],"genre_scores_gemma":[0.02605601,0.0001531249,0.5054947,0.0008841103,0.0002514579,0.0008754666,0.00004945708,0.0006877142,0.465548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9246522,"threshold_uncertainty_score":0.9994993,"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."}}