{"id":"W2065354331","doi":"10.3115/1708322.1708330","title":"Extractive vs. NLG-based abstractive summarization of evaluative text","year":2008,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Natural language processing; Margin (machine learning); Context (archaeology); Artificial intelligence; Abstraction; Natural language generation; Information retrieval; Natural language; Machine learning","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":[0.003978954,0.0009857228,0.0009047575,0.00225468,0.0003805792,0.00185837,0.000912495,0.000630554,0.001997974],"category_scores_gemma":[0.02094561,0.0002852116,0.000658287,0.002140949,0.0004648695,0.002743571,0.001080329,0.0008896298,0.00136917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004374983,"about_ca_system_score_gemma":0.0004238571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006423873,"about_ca_topic_score_gemma":0.001380503,"domain_scores_codex":[0.9971104,0.001457451,0.0003543959,0.0003924723,0.0005887033,0.00009653775],"domain_scores_gemma":[0.9845443,0.009636166,0.001697394,0.002125683,0.001798194,0.0001983159],"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":[0.002688358,0.0003998904,0.008153856,0.001990155,0.0004729488,0.0002469295,0.003080952,0.04428332,0.1405177,0.005233876,0.008731929,0.7842],"study_design_scores_gemma":[0.0004948563,0.002804042,0.04059664,0.0002409079,0.001104982,0.0007398271,0.002541518,0.6592147,0.2430997,0.0172202,0.03163673,0.0003058483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4227778,0.002984004,0.5437576,0.001317517,0.0003178481,0.001165618,0.004611932,0.01148225,0.0115855],"genre_scores_gemma":[0.6649174,0.001044848,0.3209568,0.000228443,0.0002697444,0.0005185418,0.007932482,0.0007485822,0.003383141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003978954,"threshold_uncertainty_score":0.02104294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04196349599720611,"score_gpt":0.2851438641185023,"score_spread":0.2431803681212962,"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."}}