{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008803393,0.00009174141,0.0002435974,0.0002778128,0.0000873746,0.0004003074,0.002309067,0.00004459593,0.000008031093],"category_scores_gemma":[0.01187545,0.00006763199,0.000121581,0.000190864,0.0000715411,0.0001808703,0.0002786392,0.0002316325,4.635284e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006301978,"about_ca_system_score_gemma":0.0001448159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004750324,"about_ca_topic_score_gemma":0.00001999537,"domain_scores_codex":[0.9983101,0.00006608301,0.0007051643,0.0001401628,0.0006594268,0.0001191014],"domain_scores_gemma":[0.9913113,0.0001784656,0.001165314,0.0004070305,0.006897065,0.00004084827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004028244,0.0007440196,0.3461798,0.0001807433,0.002208998,0.0001843899,0.01395523,0.4262073,0.00006079295,0.1581464,0.0005685678,0.05152348],"study_design_scores_gemma":[0.00052102,0.0000290189,0.03162314,0.0002605727,0.0001297613,0.000004533763,0.0001020177,0.9615716,0.00009628824,0.004448225,0.001093275,0.0001205374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04109427,0.0002198541,0.9303187,0.0002617288,0.004891895,0.0001858345,0.000006187314,0.0000278277,0.02299368],"genre_scores_gemma":[0.9106554,0.00001377156,0.08828773,0.00002974622,0.0009819317,0.000001501464,0.000001333803,0.00000442176,0.00002415073],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8695611,"threshold_uncertainty_score":0.9964479,"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."}}