{"id":"W4324138366","doi":"10.3233/idt-220214","title":"Tolerance-based granular methods: Foundations and applications in natural language processing","year":2023,"lang":"en","type":"article","venue":"Intelligent Decision Technologies","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Sentiment analysis; Automatic summarization; Machine translation; Named-entity recognition; Information extraction; Information retrieval; Machine learning; Task (project management)","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":[0.0004100348,0.0001306722,0.0001650598,0.0005909926,0.0001669838,0.0002196296,0.0008312485,0.0001028445,0.000002171438],"category_scores_gemma":[0.0003261742,0.00009960689,0.00004162087,0.002022951,0.0001124113,0.0002266042,0.000336496,0.0002003744,0.00003717494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003562528,"about_ca_system_score_gemma":0.00003046295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000112055,"about_ca_topic_score_gemma":0.00001568925,"domain_scores_codex":[0.998858,0.00003135379,0.0002755949,0.0004119674,0.0001842564,0.0002388209],"domain_scores_gemma":[0.9988638,0.0004708044,0.00006492264,0.0005265781,0.00005267876,0.000021231],"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":[0.000001593583,0.00001957765,0.0004282023,0.000008420038,0.000001161869,0.000007942295,0.0001966438,0.0003086685,0.0001787171,0.004447813,0.00006197123,0.9943393],"study_design_scores_gemma":[0.0003028846,0.00007105753,0.004388017,0.0001528786,0.000005921956,0.00001042755,0.003884628,0.6734491,0.02196844,0.2654833,0.02981798,0.0004654092],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01298826,0.005034785,0.9787421,0.0009910429,0.0001113342,0.000316299,0.000001772686,0.001667888,0.0001465752],"genre_scores_gemma":[0.6594073,0.0002601168,0.3401039,0.00005749879,0.000007404907,0.0001346216,0.000006109718,0.000006271564,0.00001682753],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9938739,"threshold_uncertainty_score":0.4061851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03314976492943422,"score_gpt":0.3588328957639255,"score_spread":0.3256831308344912,"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."}}