{"id":"W4389520674","doi":"10.18653/v1/2023.emnlp-main.433","title":"Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Cisco Systems","keywords":"Computer science; Leverage (statistics); Sequence (biology); Context (archaeology); Resource (disambiguation); Sample (material); Generalization; Process (computing); Artificial intelligence; Machine learning; Data mining; Programming language","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":[0.00121307,0.001974612,0.001524697,0.0008466392,0.00061025,0.001179827,0.002885339,0.001590262,0.005019992],"category_scores_gemma":[0.007789608,0.0008105885,0.001119051,0.0008848259,0.001065574,0.003178071,0.002685507,0.003355759,0.002904491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001092288,"about_ca_system_score_gemma":0.001949813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006802288,"about_ca_topic_score_gemma":0.01769461,"domain_scores_codex":[0.9990498,0.0002280599,0.00004462414,0.0003904589,0.0001777157,0.0001092447],"domain_scores_gemma":[0.9977787,0.001004064,0.0001368411,0.0006336314,0.0002940557,0.0001527596],"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":[0.0006219606,0.0005878034,0.003896819,0.0003628224,0.0001422125,0.0002999498,0.0003314991,0.414381,0.03396512,0.006761186,0.0209051,0.5177445],"study_design_scores_gemma":[0.00003938039,0.00007092521,0.0002419676,0.00001431066,0.00001747469,0.00005386462,0.00004157875,0.98537,0.005542896,0.006462558,0.002127429,0.00001749626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0542483,0.0006725941,0.9141783,0.0005559371,0.0001901336,0.0002298717,0.0009265548,0.02551844,0.003479862],"genre_scores_gemma":[0.4667762,0.0003321823,0.5156765,0.001386612,0.0001582661,0.000655412,0.005753247,0.002787094,0.006474455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006802288,"threshold_uncertainty_score":0.01679355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04192559110134546,"score_gpt":0.2735007169432181,"score_spread":0.2315751258418727,"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."}}