{"id":"W2950072837","doi":"10.48550/arxiv.1711.07632","title":"Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Computer science; Word2vec; Poetry; Context (archaeology); Artificial intelligence; Relevance (law); Natural language processing; Theme (computing); Sequence (biology); Artificial neural network; Theoretical computer science; Pattern recognition (psychology); Linguistics; History; Philosophy","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"],"consensus_categories":[],"category_scores_codex":[0.0003042308,0.0003680964,0.0003545546,0.0002358738,0.000617967,0.0003668791,0.001821429,0.0001506687,0.00003553152],"category_scores_gemma":[0.00007340353,0.0003664103,0.0001536246,0.0001556165,0.000127392,0.0007756663,0.001197871,0.0005033722,0.00001687897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002918628,"about_ca_system_score_gemma":0.0007799689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001630094,"about_ca_topic_score_gemma":0.00003646229,"domain_scores_codex":[0.9979564,0.0001053406,0.000246233,0.001106369,0.0002329127,0.0003527368],"domain_scores_gemma":[0.9975897,0.0001256688,0.0005531935,0.00136549,0.000214689,0.0001512524],"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":[0.00000595992,0.00003201274,0.002156534,0.00004842842,0.0001086292,0.0001915093,0.0001562957,0.9357611,0.00001694796,0.0614313,0.00002071182,0.00007060495],"study_design_scores_gemma":[0.0004166753,0.00001312002,0.0004885802,0.0001172059,0.00004984622,0.00004941975,0.00002683107,0.924218,0.000009673259,0.07420399,0.000006501437,0.0004001375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3007548,0.00001785761,0.6979217,0.0000807492,0.0003194177,0.0001687121,0.00001767788,0.0001187617,0.0006003724],"genre_scores_gemma":[0.8384224,0.000008810751,0.1610389,0.000106398,0.0001531474,0.000001066437,0.00003933095,0.00001902169,0.0002109709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5376676,"threshold_uncertainty_score":0.9998788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07932672630128064,"score_gpt":0.2133251980187364,"score_spread":0.1339984717174558,"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."}}