{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004987044,0.001503161,0.001275241,0.006735531,0.0007246024,0.001296506,0.0009264621,0.0009574522,0.009234997],"category_scores_gemma":[0.003138153,0.0005640762,0.001428849,0.00406592,0.0001957848,0.002218737,0.0008753251,0.001033775,0.01352628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004076666,"about_ca_system_score_gemma":0.001071287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002537901,"about_ca_topic_score_gemma":0.005940016,"domain_scores_codex":[0.9991493,0.0001220504,0.00009521972,0.0002593964,0.0002987059,0.00007529468],"domain_scores_gemma":[0.998035,0.0007247959,0.0001743001,0.0002901793,0.0006772054,0.00009847249],"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":[0.0006499365,0.0003751293,0.004881597,0.0007505398,0.0002117021,0.0009158889,0.0002348817,0.009547928,0.06277293,0.002418986,0.07957127,0.8376692],"study_design_scores_gemma":[0.0001846981,0.0004823197,0.01434383,0.0001672302,0.0006953545,0.002370948,0.0006193231,0.6937762,0.160062,0.01666712,0.1104488,0.0001822019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06226882,0.001570909,0.8224108,0.0009624486,0.0005722762,0.000856969,0.02898167,0.07543848,0.006937724],"genre_scores_gemma":[0.2281383,0.00162234,0.6647262,0.0002798869,0.0006595607,0.0008437829,0.07907272,0.003635295,0.02102188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009234997,"threshold_uncertainty_score":0.03089416,"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."}}