{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000221217,0.0001044174,0.0001505231,0.0001073371,0.00008090126,0.00001554282,0.0003654325,0.00005754545,0.00009849953],"category_scores_gemma":[0.0001168495,0.00009467171,0.00005387999,0.0002571222,0.00005997232,0.0005610838,0.00006316436,0.0001072409,0.00003713961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006390778,"about_ca_system_score_gemma":0.0002479593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001382962,"about_ca_topic_score_gemma":0.00001221429,"domain_scores_codex":[0.9988271,0.00007462128,0.0002408753,0.0003124781,0.0003902538,0.0001546488],"domain_scores_gemma":[0.9988541,0.0002434697,0.0001653995,0.000382939,0.0003038302,0.00005027984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004007529,0.002409784,0.03318528,0.0001225588,0.0003413084,0.0001496034,0.03064209,0.3022448,0.04714514,0.3093409,0.003344157,0.2706736],"study_design_scores_gemma":[0.0005739449,0.0001242791,0.04387199,0.00001799519,0.000007429221,0.000006997839,0.00008364759,0.8748868,0.07747532,0.002593547,0.0001714548,0.0001866217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07458918,0.00001658629,0.9052477,0.0003490892,0.000114408,0.000182671,0.000001657457,0.00007669701,0.01942196],"genre_scores_gemma":[0.9088436,0.000003348892,0.09057257,0.000156585,0.00002325901,0.00001009369,0.000002411167,0.000005265799,0.0003828373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8342544,"threshold_uncertainty_score":0.38606,"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."}}