{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006203337,0.0006021515,0.0004719424,0.0003026235,0.000205463,0.0004945823,0.0006968284,0.0005786173,0.002065387],"category_scores_gemma":[0.002005422,0.0003662642,0.0006604663,0.0003052753,0.0004117553,0.0008026004,0.0007258885,0.0009902172,0.0007487929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003434827,"about_ca_system_score_gemma":0.0005696994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002780432,"about_ca_topic_score_gemma":0.003856992,"domain_scores_codex":[0.999744,0.00008732737,0.00001444628,0.00007426985,0.00005061022,0.00002928511],"domain_scores_gemma":[0.9993976,0.0003611387,0.00003184241,0.00006546931,0.0001151066,0.0000288272],"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":[0.0001696103,0.0001365154,0.001358256,0.00015651,0.000111692,0.0001683003,0.0002086293,0.5916547,0.02224123,0.02039139,0.003896957,0.3595063],"study_design_scores_gemma":[0.000005265714,0.00001140765,0.00006212702,0.000002734496,0.000004537753,0.00001230169,0.00000704754,0.9955479,0.002178695,0.001840679,0.0003245935,0.000002760546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04318237,0.0002138423,0.9527315,0.0002049992,0.00006449516,0.00004288379,0.0001211198,0.001074708,0.002364059],"genre_scores_gemma":[0.6963235,0.0002592636,0.293523,0.0002154661,0.00007181051,0.0001474779,0.0008057961,0.0002923241,0.008361435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002780432,"threshold_uncertainty_score":0.00690943,"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."}}