{"id":"W6929348705","doi":"10.48448/g283-y134","title":"Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pairwise comparison; Sentence; Task (project management); Training set; Set (abstract data type); Domain (mathematical analysis); Domain adaptation","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":[0.003165818,0.003161511,0.00144176,0.001296862,0.0006867537,0.001209236,0.00287716,0.001569704,0.008732104],"category_scores_gemma":[0.008368289,0.0007830649,0.001146385,0.001212677,0.0007072556,0.00330982,0.002953276,0.00366014,0.006859901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007021714,"about_ca_system_score_gemma":0.001535573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004619799,"about_ca_topic_score_gemma":0.009505132,"domain_scores_codex":[0.997602,0.0009298259,0.0001613305,0.0006083067,0.0005413885,0.0001571789],"domain_scores_gemma":[0.9966841,0.001094612,0.0001611747,0.0008311353,0.001056397,0.000172465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005927273,0.0005490399,0.001974047,0.0003897184,0.0002506411,0.0003266137,0.0003177274,0.06581642,0.02902372,0.006351938,0.03217672,0.8622307],"study_design_scores_gemma":[0.0000753775,0.0002882923,0.000820487,0.00004700635,0.00006471355,0.0002601508,0.00008221746,0.9529593,0.02599085,0.01004722,0.00930397,0.00006050414],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02456135,0.001080014,0.9498586,0.000305773,0.0004041164,0.000209215,0.001264087,0.01841542,0.0039013],"genre_scores_gemma":[0.2591593,0.0004792059,0.7096224,0.0007357392,0.0002397513,0.0007174413,0.01044998,0.001570746,0.0170254],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008732104,"threshold_uncertainty_score":0.02921182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04312462040238894,"score_gpt":0.3671272963804491,"score_spread":0.3240026759780602,"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."}}