{"id":"W2104483432","doi":"","title":"Probabilistic Document Modeling for Syntax Removal in Text Summarization","year":2011,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Automatic summarization; Computer science; Probabilistic logic; Syntax; Artificial intelligence; Natural language processing; Metric (unit); Statistical model; Term (time); Generative model; Hidden Markov model; Generative grammar; A priori and a posteriori; Information retrieval","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":[0.0003054698,0.00007440145,0.00008742027,0.0000764247,0.00003582907,0.00004584827,0.0003594026,0.00003779042,0.00001811005],"category_scores_gemma":[0.00006223047,0.00006729206,0.00002688015,0.0001272236,0.000006097635,0.0003496426,0.0001095442,0.00004393687,0.000008969882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006339373,"about_ca_system_score_gemma":0.00004451573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002692867,"about_ca_topic_score_gemma":0.000120619,"domain_scores_codex":[0.9991413,0.00001951781,0.0002321103,0.0003018104,0.0001130392,0.0001921727],"domain_scores_gemma":[0.999532,0.00002935983,0.00003008877,0.0003211649,0.00005118172,0.00003624758],"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":[0.000009232139,0.00005051809,0.0001897038,0.00003419218,0.000003960074,0.000004905164,0.001436947,0.05832355,0.0001041979,0.9028378,0.00002151325,0.03698355],"study_design_scores_gemma":[0.0001580279,0.00001899624,0.00002372144,0.00001482667,0.000001538694,0.00000336621,0.00001928466,0.8931266,0.0001678717,0.1063297,0.00005402617,0.00008200655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02271453,0.00001504369,0.9699213,0.0001593238,0.0001551954,0.0003426316,1.968221e-7,0.00009010265,0.006601696],"genre_scores_gemma":[0.6238429,0.000001501832,0.3757689,0.00007295838,0.0000174885,0.00003318896,7.857103e-7,0.000004076527,0.0002581768],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.834803,"threshold_uncertainty_score":0.274409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05544849043075354,"score_gpt":0.253299286546898,"score_spread":0.1978507961161445,"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."}}