{"id":"W2128424286","doi":"10.1017/s1351324911000167","title":"Query-focused multi-document summarization: automatic data annotations and supervised learning approaches","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Artificial intelligence; Conditional random field; Semi-supervised learning; Supervised learning; Support vector machine; Annotation; Machine learning; Information retrieval; Natural language processing; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005368747,0.001290555,0.001335166,0.003331459,0.0008739584,0.001219368,0.001670609,0.001154359,0.0007106849],"category_scores_gemma":[0.01506733,0.0004132582,0.0009309745,0.002231134,0.0005904681,0.002876069,0.001058963,0.001357805,0.0007266281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007236545,"about_ca_system_score_gemma":0.0009036917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002113224,"about_ca_topic_score_gemma":0.00432883,"domain_scores_codex":[0.9946114,0.003017387,0.0003786155,0.0009843139,0.0008850521,0.0001232146],"domain_scores_gemma":[0.9788084,0.01188999,0.002240548,0.00278725,0.003968779,0.0003050515],"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":[0.0005805876,0.0007312857,0.003884082,0.0006151026,0.0003202702,0.0001234066,0.0006235235,0.07474454,0.02671475,0.002154268,0.004666821,0.8848415],"study_design_scores_gemma":[0.00006551621,0.0003450304,0.00308276,0.00005620153,0.0001654758,0.0001134344,0.0002058462,0.9503317,0.03599632,0.006081382,0.003491947,0.00006445294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0459548,0.001215327,0.9453755,0.0003531661,0.00006171583,0.0002056337,0.0003159566,0.005723358,0.0007945647],"genre_scores_gemma":[0.2847112,0.0004264672,0.7108411,0.0001530488,0.0001875658,0.000264697,0.001936125,0.0003060896,0.001173834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005368747,"threshold_uncertainty_score":0.02839303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05869544911709373,"score_gpt":0.2372541145684448,"score_spread":0.178558665451351,"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."}}