{"id":"W2735682218","doi":"10.5539/ijel.v7n4p33","title":"Addressing the Problem of Coherence in Automatic Text Summarization: A Latent Semantic Analysis Approach","year":2017,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Computer science; Latent semantic analysis; Coherence (philosophical gambling strategy); Information retrieval; Natural language processing; Multi-document summarization; Semantics (computer science); Artificial intelligence; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003920432,0.0007181793,0.0009516648,0.005241238,0.0008790113,0.00208612,0.0008014877,0.0007465929,0.0008135255],"category_scores_gemma":[0.01220868,0.0003317486,0.001124938,0.003018219,0.0008800661,0.003624502,0.001374575,0.00099568,0.0003311479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007008771,"about_ca_system_score_gemma":0.001407572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001205325,"about_ca_topic_score_gemma":0.001514429,"domain_scores_codex":[0.9973356,0.001385267,0.00027652,0.0004286456,0.0004677211,0.0001061965],"domain_scores_gemma":[0.9914811,0.005204963,0.00135225,0.0004843481,0.001361785,0.0001155844],"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":[0.0003848433,0.0003014321,0.007186357,0.001494311,0.000503691,0.0003078933,0.004068304,0.03724921,0.03032447,0.05520357,0.004239963,0.858736],"study_design_scores_gemma":[0.0001131243,0.0006169775,0.01241667,0.0002898319,0.0006053355,0.000342163,0.002183767,0.8081239,0.02016283,0.140543,0.01442345,0.0001789836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02647899,0.001100242,0.9704645,0.0004912479,0.00003242759,0.0001119348,0.0001772993,0.0004658262,0.0006774627],"genre_scores_gemma":[0.4274043,0.00106682,0.5685763,0.0001106152,0.0002345532,0.0003570427,0.001128808,0.0001008803,0.001020666],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005241238,"threshold_uncertainty_score":0.02073348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06497002097453258,"score_gpt":0.3178645578988425,"score_spread":0.25289453692431,"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."}}