{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006419274,0.0005758442,0.000462154,0.0003211713,0.0002073812,0.0004879492,0.0007109261,0.0005811905,0.001937379],"category_scores_gemma":[0.002068751,0.0003687641,0.0006764257,0.0003205873,0.0004131548,0.0008005172,0.0007227544,0.0009676652,0.000693503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003564303,"about_ca_system_score_gemma":0.0005658077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002900143,"about_ca_topic_score_gemma":0.003988694,"domain_scores_codex":[0.9997454,0.00009203245,0.00001400651,0.00007182527,0.00004775682,0.00002882838],"domain_scores_gemma":[0.9993629,0.0003994448,0.0000328342,0.00006287334,0.0001142008,0.00002764464],"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":[0.0001638123,0.0001353047,0.001459908,0.0001448465,0.0001077351,0.0001594403,0.0002100511,0.6359129,0.01769336,0.02072587,0.003732486,0.3195543],"study_design_scores_gemma":[0.0000048399,0.00001028322,0.00006039537,0.000002567401,0.000004162613,0.00001098382,0.000006624602,0.9960811,0.001667823,0.001864988,0.0002838409,0.000002537497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04758493,0.0002202067,0.9483906,0.0002244982,0.00006174696,0.00004390474,0.0001252709,0.0009661642,0.002382604],"genre_scores_gemma":[0.7215012,0.0002562202,0.268956,0.0002088848,0.0000713905,0.0001465092,0.0007718675,0.0002556604,0.007832309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002900143,"threshold_uncertainty_score":0.00648123,"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."}}