{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001124363,0.0006020269,0.0006239332,0.0005008137,0.0005079818,0.001559027,0.001554898,0.0004224582,0.000005687193],"category_scores_gemma":[0.0001608994,0.0005541643,0.0001213866,0.001265967,0.0004605244,0.0009976273,0.002724179,0.0008156514,0.000007285881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004080374,"about_ca_system_score_gemma":0.0007272948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000922145,"about_ca_topic_score_gemma":0.0001637548,"domain_scores_codex":[0.9957616,0.0003786908,0.0005188818,0.002091367,0.0005326854,0.0007168279],"domain_scores_gemma":[0.9975387,0.0003556928,0.0003760061,0.001162524,0.0003910352,0.0001760043],"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":[0.000004607953,0.00002776245,0.0003813262,0.00001592279,0.00001345474,0.000004844642,0.0008225043,0.8351663,0.001365774,0.0001638565,0.0000288774,0.1620047],"study_design_scores_gemma":[0.0003221009,0.00007276005,0.0008577951,0.000135505,0.00001750221,0.0000151411,6.215444e-7,0.9920187,0.003534474,0.002343328,0.00006342903,0.0006186413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01247474,0.001343286,0.9770504,0.0004883884,0.007806292,0.0007159637,0.000005555963,0.00008552618,0.00002988253],"genre_scores_gemma":[0.6772346,0.00005253349,0.3201643,0.0002155742,0.002290977,0.000009839811,0.00001230017,0.0000179223,0.000001878632],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6647599,"threshold_uncertainty_score":0.999691,"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."}}