{"id":"W2785543907","doi":"10.24963/ijcai.2018/631","title":"Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ningbo Municipal Science and Technology Innovative Research Team; Natural Sciences and Engineering Research Council of Canada; National Key Research and Development Program of China; Beijing Advanced Innovation Center for Imaging Technology","keywords":"Autoencoder; Word2vec; Computer science; Poetry; Context (archaeology); Artificial intelligence; Natural language processing; Artificial neural network; Relevance (law); Sequence (biology); Theme (computing); Recurrent neural network; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004481084,0.0003820085,0.000350299,0.0001964371,0.0002865609,0.0004714417,0.001093353,0.0001303968,0.0001961568],"category_scores_gemma":[0.00007870989,0.0002978411,0.0001100652,0.0001546874,0.00008419646,0.0004249055,0.001034094,0.0003966246,0.00002516542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000185017,"about_ca_system_score_gemma":0.0009220807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001047626,"about_ca_topic_score_gemma":0.00002234017,"domain_scores_codex":[0.9973778,0.00009102059,0.0004943532,0.000907641,0.0007756094,0.0003535784],"domain_scores_gemma":[0.9981995,0.0001468328,0.0003586862,0.0008974396,0.0002773166,0.0001202871],"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":[0.000002255869,0.0000345113,0.0005561442,0.00006897971,0.0001054091,0.00001467615,0.0003680981,0.9795532,0.00004690125,0.01881172,0.000196944,0.0002411639],"study_design_scores_gemma":[0.0002257902,0.00001588774,0.0001932828,0.0001054449,0.00001789892,0.0001252904,0.00001689782,0.946913,0.00003995001,0.05196467,0.000007194571,0.0003746772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08941321,0.00003002761,0.9075238,0.0003876026,0.0006471683,0.0002693205,0.00001483739,0.0002472564,0.001466782],"genre_scores_gemma":[0.3241053,0.000001315323,0.6747954,0.0005133554,0.0004088839,0.00002002004,0.00005263691,0.0000191201,0.0000839316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2346921,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02944076470638953,"score_gpt":0.2785390950411841,"score_spread":0.2490983303347945,"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."}}