{"id":"W2887344265","doi":"10.1109/icit.2017.12","title":"An Approach to Generic Bengali Text Summarization Using Latent Semantic Analysis","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Future Earth","funders":"","keywords":"Automatic summarization; Bengali; Latent semantic analysis; Computer science; Probabilistic latent semantic analysis; Natural language processing; Multi-document summarization; Artificial intelligence; Semantic analysis (machine learning); Information retrieval; Semantics (computer science)","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":[0.0002414093,0.00008994473,0.0001436993,0.0001804988,0.0003638301,0.0006330288,0.001043666,0.00003814222,0.000009870311],"category_scores_gemma":[0.00001712563,0.00007909873,0.00005729213,0.0003289489,0.00001081927,0.0006057788,0.0002608752,0.00004353857,0.00001049719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003393741,"about_ca_system_score_gemma":0.00002406594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007277273,"about_ca_topic_score_gemma":0.00005023346,"domain_scores_codex":[0.9989881,0.00003805647,0.000157868,0.0004220474,0.0002053017,0.0001886153],"domain_scores_gemma":[0.9983151,0.000005565938,0.00007878339,0.001429771,0.00006191961,0.0001088617],"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":[0.000001112249,0.00009899592,0.06448825,0.00001031552,0.0001152048,0.000002875807,0.000755628,0.8733394,0.005748826,0.02513628,0.00002093161,0.03028222],"study_design_scores_gemma":[0.00004757065,0.000007130419,0.03167432,0.000001828296,0.0000464001,0.000001158781,0.00001037455,0.9676377,0.0003032247,0.0001424519,0.00001452506,0.000113331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2239477,0.000005148881,0.7737201,0.0001293726,0.00007286543,0.00007137637,2.551444e-7,0.00006437046,0.001988815],"genre_scores_gemma":[0.6703205,7.517332e-7,0.3293946,0.0001104761,0.00003985612,0.000002070101,0.000002243282,0.000003683581,0.0001258429],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4463727,"threshold_uncertainty_score":0.6104311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08210903640903092,"score_gpt":0.2954794284327824,"score_spread":0.2133703920237514,"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."}}