{"id":"W4386566897","doi":"10.18653/v1/2023.eacl-demo.3","title":"NLP Workbench: Efficient and Extensible Integration of State-of-the-art Text Mining Tools","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Workbench; Computer science; Natural language processing; Biomedical text mining; Extensibility; State (computer science); Artificial intelligence; Computational linguistics; Information retrieval; Programming language; Text mining; Visualization","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002812737,0.0000536021,0.00009290005,0.00007299954,0.00003554453,0.00003980241,0.0002460548,0.00001765435,0.000006247648],"category_scores_gemma":[0.00007921679,0.00003705539,0.00002662612,0.0004494959,0.00002784114,0.000112727,0.0002355581,0.00004194849,0.0000081671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007930344,"about_ca_system_score_gemma":0.0000324777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001613272,"about_ca_topic_score_gemma":0.00001505827,"domain_scores_codex":[0.9993086,0.00002430115,0.000202047,0.0001691978,0.0001805003,0.0001153255],"domain_scores_gemma":[0.9994092,0.000120704,0.00006552946,0.0003179614,0.00006353036,0.00002308307],"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":[0.000005327032,0.00004140991,0.001844774,0.00004538189,0.00001335985,0.000002778817,0.006901117,0.05120892,0.03333215,0.04795903,0.002166817,0.8564789],"study_design_scores_gemma":[0.00009785433,0.00002457717,0.00805116,0.00006996477,0.000002053023,0.000001847562,0.0001606155,0.9662358,0.02397769,0.001123429,0.0001947832,0.00006026912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5555091,0.00001990548,0.4424521,0.0002956219,0.0001521568,0.00007259726,4.08752e-7,0.00003960024,0.001458531],"genre_scores_gemma":[0.9571314,0.000004680556,0.04136183,0.0000494886,0.000007164713,0.000002766875,3.99142e-7,0.000002779218,0.001439415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9150268,"threshold_uncertainty_score":0.1511075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04717803324324346,"score_gpt":0.2622634332073935,"score_spread":0.21508539996415,"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."}}