{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001991675,0.000129461,0.0001176685,0.0001006936,0.00007646188,0.000108404,0.0005803596,0.00004705986,0.00001078463],"category_scores_gemma":[0.0001503548,0.0001217302,0.00001797156,0.000194902,0.000009516477,0.000787949,0.0003797776,0.0002346105,0.000004795518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002436778,"about_ca_system_score_gemma":0.00001626395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006810282,"about_ca_topic_score_gemma":0.00001209307,"domain_scores_codex":[0.9991167,0.00002841609,0.0001710981,0.0003335061,0.0001486,0.0002017178],"domain_scores_gemma":[0.9993098,0.00005573693,0.00003568013,0.0005166468,0.00002020886,0.00006193858],"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":[0.000005533153,0.0001090676,0.003924672,0.0004750341,0.0001877856,0.0001563801,0.08322764,0.04773287,0.006212438,0.02912032,0.00004466962,0.8288036],"study_design_scores_gemma":[0.0002251502,0.000007570461,0.002344265,0.00002713925,0.000006953552,0.000009617103,0.0002002449,0.9966418,0.0003330386,0.000009376288,0.00004266895,0.0001521971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1015578,0.001824471,0.8955594,0.00006999616,0.0002366675,0.0001489102,0.000002003585,0.0005202884,0.00008051448],"genre_scores_gemma":[0.6284912,0.000003520428,0.3713564,0.00001505737,0.00003050302,0.000006009132,0.00002385777,0.000008885814,0.00006457208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9489089,"threshold_uncertainty_score":0.4964014,"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."}}