{"id":"W4385573784","doi":"10.18653/v1/2022.emnlp-industry.39","title":"Developing Prefix-Tuning Models for Hierarchical Text Classification","year":2022,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Prefix; Computer science; Hierarchy; Task (project management); Set (abstract data type); Key (lock); Process (computing); Artificial intelligence; Machine learning; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003057573,0.00008913382,0.00009297154,0.0001705906,0.0005395554,0.0001320659,0.001103975,0.00003593189,0.0000293347],"category_scores_gemma":[0.00004097704,0.00008557893,0.00004692981,0.0004247732,0.0000334256,0.0005259709,0.0005561406,0.000142131,0.000009263143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528307,"about_ca_system_score_gemma":0.0001210045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003077938,"about_ca_topic_score_gemma":0.000001011468,"domain_scores_codex":[0.9989063,0.00003932638,0.0002173901,0.0003738044,0.0002410766,0.0002221323],"domain_scores_gemma":[0.9992342,0.0001305852,0.00008606177,0.0004672421,0.00005042555,0.00003147944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002987472,0.00001763525,0.00002884376,0.000003676947,0.000003901278,1.698105e-7,0.000147555,0.0003497925,0.0006941575,0.9084231,0.001619302,0.08870883],"study_design_scores_gemma":[0.0001775217,0.00004778354,0.0002603413,0.000001909868,0.000001550376,0.000003384221,0.0003295362,0.6037657,0.001007362,0.3465093,0.04775461,0.0001409483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001069807,0.00003797189,0.9746034,0.01796626,0.0001576597,0.0002829207,0.00000212604,0.0009476923,0.004932142],"genre_scores_gemma":[0.6765091,0.000006201662,0.3210958,0.0004144089,0.00001209527,0.0004922568,0.000009602016,0.000006455573,0.001454081],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6754392,"threshold_uncertainty_score":0.4149878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1023431142075761,"score_gpt":0.3022484223928824,"score_spread":0.1999053081853063,"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."}}