{"id":"W4366127141","doi":"10.1007/978-3-031-25759-9_12","title":"Human-Centric Question-Answering System with Linguistic Terms","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Question answering; Computer science; Artificial intelligence; Natural language; Natural (archaeology); Natural language processing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075648,0.0005629075,0.001105901,0.001126386,0.0007151189,0.001654758,0.001606113,0.001227161,0.01016129],"category_scores_gemma":[0.001611095,0.0003412332,0.0006902763,0.001297148,0.0003569442,0.00323169,0.001589513,0.0008417973,0.006195573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006344407,"about_ca_system_score_gemma":0.001013875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002124805,"about_ca_topic_score_gemma":0.002567495,"domain_scores_codex":[0.9993781,0.0001523122,0.00004504472,0.0002455893,0.0001309191,0.00004807114],"domain_scores_gemma":[0.9993698,0.0002719477,0.00002690788,0.0001360352,0.0001338541,0.00006142867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001322566,0.0007959935,0.003508355,0.0007754061,0.0002533795,0.0005845302,0.001347922,0.007621367,0.1536003,0.02754649,0.1007071,0.7019366],"study_design_scores_gemma":[0.0002980081,0.0004603867,0.004806629,0.00008177696,0.0005256503,0.001272231,0.0006602966,0.6938575,0.1259646,0.05390038,0.1180408,0.0001317448],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05266939,0.001381807,0.8777651,0.0008458011,0.0002096763,0.0004605664,0.003078883,0.0469882,0.01660065],"genre_scores_gemma":[0.330666,0.0005268182,0.6324762,0.0008236446,0.0002388283,0.000439203,0.007926595,0.0008518805,0.02605085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01016129,"threshold_uncertainty_score":0.03399289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1077463321286745,"score_gpt":0.3556728525025759,"score_spread":0.2479265203739014,"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."}}