{"id":"W2891521313","doi":"10.5555/3327757.3327855","title":"Towards Text Generation with Adversarially Learned Neural Outlines","year":2018,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Autoregressive model; Artificial intelligence; Generative grammar; Sentence; Generative model; Multinomial distribution; Natural language processing; Latent variable; Machine learning; Prior probability; Bayesian probability; Statistics; 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"],"consensus_categories":[],"category_scores_codex":[0.0005203459,0.0003112686,0.0002785594,0.0002814743,0.0003275958,0.0004501216,0.00113283,0.0001921153,0.00002391671],"category_scores_gemma":[0.0001225301,0.0002702193,0.00009189932,0.000559472,0.0001065008,0.0009029774,0.0003654535,0.0002845668,0.00003579561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002131522,"about_ca_system_score_gemma":0.0003504823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004153569,"about_ca_topic_score_gemma":0.003172661,"domain_scores_codex":[0.9976541,0.0001260203,0.0003925111,0.000702495,0.0004864719,0.0006383439],"domain_scores_gemma":[0.9979897,0.00003334339,0.0001848217,0.001265434,0.0002892515,0.0002374281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002211198,0.0003523672,0.0133389,0.00003757534,0.0001319977,0.0002000014,0.002848378,0.02928405,0.04589879,0.2514205,0.003982674,0.6522837],"study_design_scores_gemma":[0.0005144347,0.0003397673,0.003245462,0.00001688543,0.00001401073,0.0001329889,0.00002586666,0.9785724,0.01370059,0.001338462,0.001729507,0.0003696262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08176786,0.000151145,0.9071068,0.008128635,0.0003620611,0.0004038384,0.000003459769,0.000976764,0.001099393],"genre_scores_gemma":[0.6479601,0.00001300445,0.3487402,0.001992031,0.0006679754,0.0000851529,0.000005669564,0.00002856742,0.0005073051],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9492884,"threshold_uncertainty_score":0.999975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02322451125486854,"score_gpt":0.2462142602693015,"score_spread":0.2229897490144329,"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."}}