{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001056232,0.001315065,0.0006415169,0.0004107089,0.0003322975,0.0004164226,0.001289811,0.001171304,0.003657006],"category_scores_gemma":[0.002519212,0.0004936382,0.0005596863,0.0003132991,0.0007622096,0.001001216,0.001250601,0.001992902,0.001183341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006138684,"about_ca_system_score_gemma":0.0007153411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002808708,"about_ca_topic_score_gemma":0.005338497,"domain_scores_codex":[0.9996228,0.0001784927,0.0000121859,0.00007903926,0.00007032097,0.00003717644],"domain_scores_gemma":[0.9992059,0.000583082,0.00004011022,0.00007530641,0.00007117559,0.00002433582],"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":[0.0001644638,0.00008159596,0.0005225955,0.0001309419,0.00007893753,0.0002073953,0.0001281731,0.7978855,0.009530429,0.02212546,0.01022101,0.1589235],"study_design_scores_gemma":[0.00001078039,0.00001952743,0.00004299706,0.000008780736,0.000005156333,0.00003099284,0.00000479635,0.9893801,0.001411167,0.00804216,0.001037463,0.000006066348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008270391,0.0004545569,0.9857874,0.0003396923,0.00008578245,0.00009584959,0.0002060404,0.001924814,0.002835497],"genre_scores_gemma":[0.5092906,0.0006426626,0.4720724,0.001231337,0.000169201,0.0006189394,0.001637639,0.0007385866,0.01359867],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003657006,"threshold_uncertainty_score":0.01223391,"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."}}