{"id":"W2086038979","doi":"10.1016/j.eswa.2014.09.015","title":"A novel contextual topic model for multi-document summarization","year":2014,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Information overload; Multi-document summarization; Context (archaeology); Artificial intelligence; Word (group theory); Topic model; Natural language processing; Information retrieval; World Wide Web; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001690465,0.0001161374,0.0001435107,0.00005051776,0.00018202,0.0001270078,0.0004558448,0.00004995251,5.812812e-7],"category_scores_gemma":[0.00001382029,0.00009747886,0.00003032436,0.0001184853,0.00001745715,0.0002095408,0.00005603121,0.00004225877,0.00001008696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005818424,"about_ca_system_score_gemma":0.0000544286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001108412,"about_ca_topic_score_gemma":0.00003144851,"domain_scores_codex":[0.9989898,0.00001675605,0.0002460545,0.0003936655,0.000163844,0.0001898732],"domain_scores_gemma":[0.9989423,0.0000582355,0.0001008743,0.0006751966,0.000144315,0.00007906386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003078875,0.00008064308,0.00005778047,0.00002991629,0.00001511132,3.958486e-8,0.001689696,0.0351623,0.00177627,0.9524875,0.0002876443,0.008409989],"study_design_scores_gemma":[0.000596421,0.00002198216,0.00001403853,0.00001869415,0.00000274298,0.000004132374,0.00005417229,0.9812568,0.0001153275,0.0003584606,0.0174266,0.0001306591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000101492,0.000102068,0.9974769,0.0004482644,0.00009434408,0.001354602,0.000004231412,0.0001670482,0.0002510037],"genre_scores_gemma":[0.4839319,0.000002066816,0.5100896,0.0002299924,0.0001463203,0.004269325,0.00001249268,0.00001212776,0.001306206],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9521291,"threshold_uncertainty_score":0.3975073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0467911233113684,"score_gpt":0.290877761885536,"score_spread":0.2440866385741676,"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."}}