{"id":"W2808873503","doi":"10.1109/taslp.2019.2943018","title":"BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation","year":2019,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Generator (circuit theory); Discriminator; Process (computing); Sentence; Adversarial system; Generative grammar; Encoder; Joint (building)","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":[0.0002230149,0.0002081709,0.0002159669,0.0001067709,0.0004128192,0.000299298,0.0002682651,0.0001169355,0.00002203885],"category_scores_gemma":[0.00003580996,0.0001954304,0.00005944648,0.0002297539,0.00008056873,0.0003958194,0.00001257001,0.0002740576,0.000008683194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003519352,"about_ca_system_score_gemma":0.00008566307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006836223,"about_ca_topic_score_gemma":0.00005484265,"domain_scores_codex":[0.9986717,0.00005331181,0.000234061,0.0005821617,0.0001732099,0.0002855905],"domain_scores_gemma":[0.9991543,0.0001450367,0.0001136354,0.000343888,0.0001105246,0.0001326532],"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":[0.00005554128,0.00007481265,0.0001298791,0.00007162697,0.0000389109,0.000004676089,0.001925293,0.01458153,0.03761536,0.0003315321,0.00003757914,0.9451333],"study_design_scores_gemma":[0.001156343,0.0001806556,0.0002668929,0.00005089014,0.00003077919,0.00005466424,0.0002068005,0.9852209,0.01214107,0.0002208975,0.0001842767,0.0002858114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1028166,0.000263688,0.8944892,0.001372852,0.0002135697,0.0005502439,0.0000143221,0.0001549779,0.0001245456],"genre_scores_gemma":[0.7315705,0.00002344153,0.267496,0.0004753686,0.0001569259,0.0000628491,0.0000113363,0.00001496795,0.0001886576],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9706394,"threshold_uncertainty_score":0.7969419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01274127068693143,"score_gpt":0.2707468446229923,"score_spread":0.2580055739360609,"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."}}