{"id":"W2984811147","doi":"10.18653/v1/d19-5627","title":"Transformer and seq2seq model for Paraphrase Generation","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Alberta Innovates; University of Lethbridge","keywords":"Paraphrase; Computer science; Transformer; Encoder; Sentence; Artificial intelligence; Natural language processing; Decoding methods; Speech recognition; Algorithm; Engineering; Voltage; Electrical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00008147926,0.00004208765,0.00004829775,0.00002200612,0.00002760485,0.00004576012,0.00009772415,0.00002334888,0.000006083741],"category_scores_gemma":[0.000001495592,0.00003496511,0.00001819747,0.00002654248,0.000003354932,0.0002848739,0.00000924096,0.00001855483,0.000006748887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005503993,"about_ca_system_score_gemma":0.00001950091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005289573,"about_ca_topic_score_gemma":0.00001075656,"domain_scores_codex":[0.9996048,0.000003563177,0.00007249165,0.0001723083,0.00005645427,0.00009044272],"domain_scores_gemma":[0.9997782,0.00001061823,0.000009001631,0.0001564079,0.00001782832,0.00002795549],"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":[0.000005157727,0.00002304327,0.0003612308,0.0000338862,0.00001053263,2.971965e-7,0.001767925,0.08990011,0.03870587,0.7643382,0.0008347859,0.104019],"study_design_scores_gemma":[0.0002074651,0.00001349144,0.00001076992,0.000001062002,0.000001162396,0.000001131555,0.00000384392,0.99274,0.002823612,0.003904223,0.0002383892,0.00005479773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1377167,0.00002149651,0.8604487,0.0004884806,0.00006941889,0.0001632441,5.775702e-7,0.00003639447,0.001054929],"genre_scores_gemma":[0.7562383,0.000004210981,0.2419219,0.0003961948,0.00002043893,0.00001040074,9.188811e-7,0.000002149399,0.001405571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.90284,"threshold_uncertainty_score":0.1425836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04541572854080542,"score_gpt":0.2551178433031982,"score_spread":0.2097021147623928,"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."}}