{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007806464,0.0000334236,0.00004467212,0.00001988404,0.0001447041,0.00007675336,0.0006466645,0.00001631404,0.00001837117],"category_scores_gemma":[0.00008482007,0.000028134,0.00002124502,0.00002163602,0.00002119255,0.0002266605,0.0001443736,0.00005273579,0.00003359522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006051852,"about_ca_system_score_gemma":0.00001385771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001139589,"about_ca_topic_score_gemma":0.00005086774,"domain_scores_codex":[0.9996668,0.0000123636,0.00006703525,0.0001124533,0.00008545526,0.00005596232],"domain_scores_gemma":[0.9992081,0.00001423648,0.00008196318,0.0006492967,0.00002912286,0.00001728778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003491461,0.00005843146,0.008285578,0.000007286211,0.00001680187,0.000002337075,0.001518068,0.0005307376,0.2692534,0.4413786,0.00126748,0.2776778],"study_design_scores_gemma":[0.0002168923,0.00001054198,0.09975242,0.000001512885,0.000001614029,0.000001335685,0.000005742515,0.8805943,0.01890002,0.000172519,0.0002848238,0.00005824633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5391355,0.00002622411,0.4420946,0.002196226,0.0004060755,0.0000984804,8.490501e-7,0.0001016466,0.0159404],"genre_scores_gemma":[0.9201492,3.43185e-7,0.07928457,0.00004331332,0.00009899986,0.000003171241,0.000001948725,0.000001671361,0.0004167521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8800636,"threshold_uncertainty_score":0.1722725,"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."}}