{"id":"W4392981047","doi":"10.1109/icaiccit60255.2023.10466068","title":"Exploring the Effectiveness of Various Deep Learning Techniques for Text Generation in Natural Language Processing","year":2023,"lang":"en","type":"article","venue":"","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sheridan College","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Natural language; Natural language generation; Natural (archaeology); Deep learning; History","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":[0.0008314122,0.00004796543,0.00008518892,0.0001849318,0.00009478737,0.00003344443,0.0003041505,0.00002798806,4.621416e-7],"category_scores_gemma":[0.0001510275,0.00003245657,0.00002632069,0.0008072098,0.00002061077,0.000408598,0.0001172049,0.0001038643,0.000001708059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001464638,"about_ca_system_score_gemma":0.00001010639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005594417,"about_ca_topic_score_gemma":0.0001119342,"domain_scores_codex":[0.9994971,0.00008194858,0.00009520948,0.0001550074,0.00006318593,0.0001076054],"domain_scores_gemma":[0.9995658,0.0001989933,0.00003448995,0.0001650294,0.00003017097,0.000005495538],"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":[0.000009280411,0.00001428155,0.001337829,0.00006554665,0.00001254696,0.000004769591,0.00148954,0.000814687,0.06936137,0.01259333,0.000008963707,0.9142879],"study_design_scores_gemma":[0.0001075795,0.00003760949,0.01049193,0.00002913659,0.000006461143,0.000002495149,0.0003651519,0.6932318,0.2948932,0.0006820188,0.00006984091,0.00008275922],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3434139,0.0001276764,0.6558246,0.00008870212,0.0000300901,0.0001298964,2.203956e-7,0.0003287342,0.00005622257],"genre_scores_gemma":[0.9847195,0.000009117856,0.01507179,0.00001148563,0.00001324504,0.0001308821,0.00001005148,0.000003221828,0.00003069671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9142051,"threshold_uncertainty_score":0.1323541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02836353976216678,"score_gpt":0.2812325212223784,"score_spread":0.2528689814602116,"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."}}