{"id":"W2929742901","doi":"10.18653/v1/w19-4303","title":"Generative Adversarial Networks for Text Using Word2vec Intermediaries","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Vector Institute; Canadian Institute for Advanced Research","keywords":"Generative grammar; Word2vec; Computer science; Adversarial system; Vocabulary; Artificial intelligence; Estimator; Word (group theory); Sentence; Generative adversarial network; Machine learning; Natural language processing; Theoretical computer science; Deep learning; Embedding; Mathematics; Linguistics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005063477,0.0006322738,0.0008249625,0.0001808059,0.0002854866,0.001002095,0.001826916,0.0005590424,0.00007688426],"category_scores_gemma":[0.0001540236,0.000555569,0.0004985197,0.0002155215,0.0002101867,0.0005588749,0.002992572,0.00062586,0.00002234991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001903304,"about_ca_system_score_gemma":0.0005106666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001033789,"about_ca_topic_score_gemma":0.00005126711,"domain_scores_codex":[0.9967938,0.0002328451,0.0005982888,0.00135204,0.0003129137,0.0007101023],"domain_scores_gemma":[0.997257,0.0004823981,0.0004265002,0.00128359,0.0003921679,0.0001583226],"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":[0.00005636372,0.00004708448,0.00004613109,0.00004466042,0.0002802383,0.000004467985,0.0005776357,0.9558455,0.0001951162,0.01090962,0.0118019,0.02019128],"study_design_scores_gemma":[0.0005355927,0.00007824475,0.00002405434,0.0001081835,0.00006756387,0.000002891234,0.00004719622,0.9881409,0.001340635,0.004471175,0.004508544,0.0006750103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002540174,0.0004271276,0.9827922,0.0006876385,0.01274716,0.001589073,0.00003029918,0.0001781706,0.00129431],"genre_scores_gemma":[0.3774625,0.00007243632,0.6152565,0.0009257455,0.004405248,0.0001619235,0.00007502049,0.00006174955,0.001578845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3772085,"threshold_uncertainty_score":0.9996896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03113695352834597,"score_gpt":0.2696983701654211,"score_spread":0.2385614166370751,"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."}}