{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009030888,0.0002635097,0.0002197801,0.0001883082,0.0002270483,0.0000988358,0.000887749,0.0002155502,0.0000497992],"category_scores_gemma":[0.0004471795,0.0002682405,0.00007981932,0.0002627801,0.0002641847,0.00001117109,0.0005007746,0.00009012194,0.000001994944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006841591,"about_ca_system_score_gemma":0.0007840021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001822988,"about_ca_topic_score_gemma":0.001347641,"domain_scores_codex":[0.9977345,0.00004077697,0.0002997153,0.001177791,0.0002932036,0.0004540151],"domain_scores_gemma":[0.9983479,0.00003632114,0.0002731305,0.0009873463,0.000222562,0.000132685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008230822,0.0001925339,0.0001436576,0.0006640322,0.0001621827,0.000002194908,0.00005965908,0.00234364,0.8066887,0.0005609838,0.1052315,0.08386856],"study_design_scores_gemma":[0.001412583,0.0002715682,0.00002505664,0.0001416285,0.0001262936,0.00001328956,0.0005114348,0.7960008,0.01261866,0.0001479624,0.1881031,0.0006275968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008161616,0.0009058844,0.9939431,0.0002570132,0.0008127469,0.0008897139,0.0006254928,0.00003941208,0.002445015],"genre_scores_gemma":[0.003110826,0.0003022684,0.8600837,0.0008271164,0.0008619906,0.0001719614,0.01234359,0.0002683488,0.1220302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7940701,"threshold_uncertainty_score":0.999977,"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."}}