{"id":"W4287329802","doi":"10.5281/zenodo.4530713","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Natural language; Natural (archaeology); Software engineering; Software; Programming language; Natural language processing; Linguistics; History; Philosophy; Archaeology","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":[0.0122114,0.001233989,0.000949849,0.002832887,0.001138719,0.00352442,0.001771943,0.002204957,0.005585156],"category_scores_gemma":[0.06294127,0.0008119422,0.0008000821,0.001138524,0.001349739,0.00523945,0.003346916,0.001777156,0.002755703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001653408,"about_ca_system_score_gemma":0.001455073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003045927,"about_ca_topic_score_gemma":0.003132743,"domain_scores_codex":[0.9833521,0.009645714,0.002021723,0.001401198,0.002805561,0.0007737226],"domain_scores_gemma":[0.9133174,0.06319896,0.003548014,0.007069445,0.01011447,0.002751672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.03636756,0.01050669,0.03137073,0.009769661,0.001039781,0.001383569,0.03846999,0.0299765,0.2002701,0.02614267,0.02682077,0.587882],"study_design_scores_gemma":[0.004624942,0.02919951,0.1402873,0.002172379,0.001723553,0.001721731,0.0213757,0.3467128,0.3216603,0.02100011,0.1080846,0.001437136],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8776124,0.001072089,0.07923511,0.0004398897,0.0002908187,0.003418715,0.003490388,0.01853605,0.01590449],"genre_scores_gemma":[0.9058143,0.0003238766,0.07561661,0.0002287695,0.00005787737,0.002716858,0.007468625,0.002704552,0.005068399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0122114,"threshold_uncertainty_score":0.0645808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06446170189282002,"score_gpt":0.302432844689339,"score_spread":0.237971142796519,"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."}}