{"id":"W2964028737","doi":"10.18653/v1/w17-2629","title":"Adversarial Generation of Natural Language","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal; Polytechnique Montréal","funders":"Nvidia","keywords":"Natural language generation; Computer science; Adversarial system; Natural language; Context (archaeology); Artificial intelligence; Generative grammar; Probabilistic logic; Natural language understanding; Natural language processing; Rule-based machine translation; Sentence; Language model; Estimator; Theoretical computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001159406,0.000791035,0.0004655172,0.0003974449,0.0002697604,0.000473501,0.0009285892,0.0006999807,0.00394907],"category_scores_gemma":[0.0056466,0.0002348956,0.0006066897,0.0003346239,0.0008089087,0.0007808216,0.001109599,0.00138366,0.0008216387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005327277,"about_ca_system_score_gemma":0.0005712312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000974897,"about_ca_topic_score_gemma":0.001572685,"domain_scores_codex":[0.9993485,0.0002887538,0.00002013239,0.0001561744,0.0001334642,0.00005298921],"domain_scores_gemma":[0.9978268,0.001599092,0.0000952229,0.0002557641,0.0001715101,0.00005156194],"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":[0.0001589577,0.0001027337,0.001109217,0.0001649934,0.00005882899,0.0004135164,0.0002100442,0.8357794,0.01028729,0.06765134,0.0120917,0.0719719],"study_design_scores_gemma":[0.00001142157,0.00002059786,0.00009180346,0.000009957861,0.000005149317,0.00004657878,0.00001340179,0.9744613,0.002085711,0.02148881,0.001757986,0.000007205822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05130355,0.0003686561,0.9374415,0.0006351719,0.0001784466,0.0001983738,0.0008069893,0.001866954,0.007200435],"genre_scores_gemma":[0.7993308,0.0003201344,0.185808,0.0006291973,0.0001041514,0.0006066567,0.002659809,0.0004753925,0.01006595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00394907,"threshold_uncertainty_score":0.01321095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02246753577189608,"score_gpt":0.3164347830586666,"score_spread":0.2939672472867705,"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."}}