{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004062647,0.002955189,0.001512184,0.007039862,0.001374323,0.003805136,0.003524877,0.001394066,0.01690217],"category_scores_gemma":[0.01231153,0.001572152,0.001380596,0.004923414,0.0006485722,0.007283056,0.005377688,0.002063764,0.02036791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005843471,"about_ca_system_score_gemma":0.001789358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003761985,"about_ca_topic_score_gemma":0.005534398,"domain_scores_codex":[0.9976358,0.0005287891,0.000412182,0.0005956135,0.0007378274,0.00008976652],"domain_scores_gemma":[0.9949145,0.002701353,0.0002136776,0.0011178,0.0007501768,0.0003024167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001066462,0.0005469079,0.002757466,0.001721677,0.0005700695,0.001349327,0.001308028,0.003926083,0.02309869,0.008870714,0.482877,0.4719076],"study_design_scores_gemma":[0.001101795,0.0003938932,0.004420422,0.0005489352,0.0004051854,0.001361382,0.001367176,0.2581569,0.07839089,0.05046644,0.6030011,0.0003859889],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.005897163,0.00109719,0.5305277,0.000829573,0.0006107974,0.0009231953,0.04658902,0.406267,0.00725836],"genre_scores_gemma":[0.05312376,0.001503533,0.683837,0.0009267497,0.000331682,0.002904666,0.2125083,0.03097976,0.01388467],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01690217,"threshold_uncertainty_score":0.05654341,"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."}}