{"id":"W4385571422","doi":"10.18653/v1/2023.findings-acl.426","title":"“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Global Water Futures; Canada First Research Excellence Fund","keywords":"Computer science; Artificial intelligence; Classifier (UML); Deep neural networks; Parametric statistics; Artificial neural network; k-nearest neighbors algorithm; Machine learning; Data mining; Pattern recognition (psychology)","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":[0.0009557652,0.002037388,0.001051244,0.002648813,0.0009311497,0.001394774,0.002812257,0.001636125,0.007673041],"category_scores_gemma":[0.005140787,0.0004998127,0.000798265,0.002703169,0.0009278401,0.005249881,0.002052201,0.002948876,0.006624766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095939,"about_ca_system_score_gemma":0.001370199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00417255,"about_ca_topic_score_gemma":0.006595133,"domain_scores_codex":[0.9990485,0.0001243739,0.00007876486,0.0003462592,0.0002994866,0.000102548],"domain_scores_gemma":[0.9979854,0.0005534391,0.0002059008,0.0006599917,0.0005001136,0.00009512802],"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":[0.0004046058,0.0002009112,0.001173521,0.0001546063,0.00004166958,0.0001390795,0.0001469066,0.01424831,0.01196962,0.003860558,0.02185198,0.9458082],"study_design_scores_gemma":[0.0001068904,0.0001633504,0.001218688,0.00005872271,0.00005891635,0.0002631476,0.0002005548,0.9353263,0.02609794,0.01684964,0.01959754,0.00005836277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06169872,0.00136637,0.9019156,0.00136709,0.0006515422,0.0005143379,0.001991788,0.02356505,0.006929581],"genre_scores_gemma":[0.3039938,0.0008731299,0.6553461,0.001064061,0.0007804277,0.0007730841,0.00790491,0.001371695,0.02789276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007673041,"threshold_uncertainty_score":0.02566892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04413472812042506,"score_gpt":0.3074148113399623,"score_spread":0.2632800832195373,"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."}}