{"id":"W1965221819","doi":"10.1016/j.patcog.2009.06.003","title":"Personalized text snippet extraction using statistical language models","year":2009,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China","keywords":"Snippet; Computer science; Automatic summarization; Information retrieval; Process (computing); Language model; Personalized search; Question answering; Identification (biology); Information extraction; Text graph; Task (project management); Search engine; Natural language processing; Artificial intelligence","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":[0.0001645248,0.0001061113,0.0001099661,0.00008069927,0.00007960585,0.0001137127,0.0001589324,0.00005609168,0.000118432],"category_scores_gemma":[0.00001911227,0.0001098488,0.00003852999,0.00009099561,0.00001204558,0.0006598364,0.00002556867,0.0001272042,0.00009491517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005901904,"about_ca_system_score_gemma":0.00002142507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008877007,"about_ca_topic_score_gemma":0.000005985395,"domain_scores_codex":[0.9989849,0.00007298625,0.0001852853,0.0003132161,0.0002299882,0.0002135683],"domain_scores_gemma":[0.9995667,0.00004921484,0.00006942554,0.0001982368,0.00004986447,0.00006658569],"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":[0.000005895437,0.00005057092,0.000040943,0.000009118466,0.000004888548,0.00003617331,0.0008591598,0.0003164842,0.00551584,0.000646501,0.00003502385,0.9924794],"study_design_scores_gemma":[0.0003256219,0.00003679621,0.0003931276,0.00004571554,0.00001062559,0.0000797594,0.00008356741,0.9817,0.0014683,0.01566017,0.00002652773,0.0001697884],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1925612,0.00004036248,0.8061783,0.0002132653,0.0001478379,0.00008934158,0.00001315208,0.00009935731,0.0006571682],"genre_scores_gemma":[0.8974336,0.000008221324,0.1017339,0.0006237715,0.0001293839,0.00000392217,0.00003477541,0.000006427793,0.00002601745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923096,"threshold_uncertainty_score":0.4479503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07131953149087347,"score_gpt":0.3179028102173276,"score_spread":0.2465832787264542,"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."}}