{"id":"W3005700414","doi":"10.1016/j.ins.2020.02.040","title":"Plausibility-promoting generative adversarial network for abstractive text summarization with multi-task constraint","year":2020,"lang":"en","type":"article","venue":"Information Sciences","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Shenzhen Institutes of Advanced Technology Innovation Program for Excellent Young Researchers; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Automatic summarization; Artificial intelligence; Discriminative model; Natural language processing; Generative grammar; Discriminator; Generative model; Classifier (UML); Inference; Adversarial system; Task (project management); Coreference; Machine learning; Resolution (logic)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000668889,0.0001078335,0.0001182439,0.00004955138,0.0004415059,0.0004543822,0.0004809808,0.0000437259,0.000006367374],"category_scores_gemma":[0.0002689753,0.00008475741,0.00003020937,0.0004695931,0.0001475452,0.003999721,0.00009092732,0.00008800634,0.00001570734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003818917,"about_ca_system_score_gemma":0.0002814597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003013385,"about_ca_topic_score_gemma":0.00001932806,"domain_scores_codex":[0.9987586,0.00003428675,0.0003556511,0.0002583017,0.0003524145,0.0002407928],"domain_scores_gemma":[0.9991147,0.000155578,0.0002884313,0.0001314328,0.0002213672,0.00008848717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005471931,0.00003048578,0.002215649,0.00005422886,0.00003111442,0.000001156534,0.058467,0.7391356,0.000505041,0.06855894,0.0003381561,0.1306078],"study_design_scores_gemma":[0.0004927023,0.0001473046,0.0005118459,0.00001431563,0.000003219481,0.000002459426,0.0009599939,0.9954748,0.0007023219,0.0006105902,0.0009539768,0.0001264612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01310786,0.000005466334,0.9831682,0.001873827,0.0002344902,0.000491794,0.000009973197,0.0001028645,0.001005495],"genre_scores_gemma":[0.6619401,6.473054e-7,0.3369801,0.0009357838,0.0001099411,0.00001968873,0.000009693241,0.000001489414,0.000002527566],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6488323,"threshold_uncertainty_score":0.4381618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05164979807439075,"score_gpt":0.2774656492488205,"score_spread":0.2258158511744298,"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."}}