{"id":"W2943468268","doi":"10.1007/978-3-030-18305-9_9","title":"TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Automatic summarization; Generator (circuit theory); Generative grammar; Artificial intelligence; Representation (politics); Natural language processing; Machine translation; Text generation; Translation (biology); Word (group theory); Adversarial system; Measure (data warehouse); BLEU; Language model; Exploit; Machine learning; Data mining; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001070446,0.001350672,0.001060333,0.0008160255,0.0004011427,0.001241735,0.002409112,0.002211967,0.01363868],"category_scores_gemma":[0.004393598,0.0007623935,0.001143246,0.0008265722,0.0006923883,0.002172658,0.002334937,0.002880244,0.006500173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007177828,"about_ca_system_score_gemma":0.000774095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002264548,"about_ca_topic_score_gemma":0.003895568,"domain_scores_codex":[0.9992326,0.000211034,0.00003439503,0.0002695829,0.0001890277,0.0000633024],"domain_scores_gemma":[0.9986874,0.0007581107,0.00004356339,0.0002994732,0.0001625472,0.00004889321],"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":[0.0005531223,0.0002638377,0.0004119125,0.0004169787,0.0001649009,0.0002990198,0.0001083205,0.3504904,0.01425131,0.03233392,0.06443259,0.5362737],"study_design_scores_gemma":[0.00003095243,0.0000216331,0.00004759308,0.00001299212,0.000009731814,0.00004556747,0.000006393378,0.9779512,0.004458737,0.01406173,0.003344096,0.000009396324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004063278,0.0004341287,0.9781526,0.0003651973,0.0002754653,0.0001683789,0.001219093,0.01216275,0.003159241],"genre_scores_gemma":[0.2099886,0.0005430785,0.754469,0.0009465083,0.0002945821,0.0006581172,0.008341085,0.003104972,0.02165393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01363868,"threshold_uncertainty_score":0.04562593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02682350185918448,"score_gpt":0.2701453311191642,"score_spread":0.2433218292599797,"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."}}