{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009922349,0.001289705,0.0007613542,0.001011067,0.0003593784,0.0008528596,0.002016245,0.001325933,0.007682535],"category_scores_gemma":[0.002430721,0.0004303927,0.001278516,0.0009209242,0.0003989639,0.002260544,0.0009642885,0.001710768,0.004049168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008129203,"about_ca_system_score_gemma":0.001170111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005477617,"about_ca_topic_score_gemma":0.01101751,"domain_scores_codex":[0.9995277,0.0001339382,0.0000408338,0.0001564846,0.00009498273,0.00004610839],"domain_scores_gemma":[0.9993771,0.0002295529,0.00004120488,0.0001223688,0.0001863646,0.00004347507],"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":[0.0005973261,0.0004107282,0.002806005,0.0006236779,0.00026134,0.0008930291,0.0003570902,0.2655666,0.0354747,0.02492793,0.03998202,0.6280996],"study_design_scores_gemma":[0.00002598091,0.00008903263,0.0002689237,0.00001153297,0.00003073047,0.0001807534,0.00002890656,0.9760957,0.008990348,0.01020275,0.004058264,0.00001719761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03088171,0.00144992,0.9443419,0.00080876,0.0002988642,0.0003533703,0.003218378,0.01263132,0.006015737],"genre_scores_gemma":[0.5118039,0.00110852,0.4539595,0.0008194626,0.0002034448,0.0007137937,0.01131211,0.0010257,0.01905358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007682535,"threshold_uncertainty_score":0.02570063,"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."}}