{"id":"W6949819765","doi":"10.5281/zenodo.4733030","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":"Natural language; Scripting language; Chatbot; Software; Natural (archaeology); Software development","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":[0.0002205741,0.00007969456,0.0001300021,0.0001871538,0.0003494496,0.0002884376,0.0006840994,0.00003519911,0.0003334328],"category_scores_gemma":[0.0006823086,0.00008765764,0.00004096691,0.0005864379,0.00002144758,0.0004411116,0.0007311348,0.0001901674,0.000124344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001967064,"about_ca_system_score_gemma":0.00000519322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006601093,"about_ca_topic_score_gemma":0.00000259216,"domain_scores_codex":[0.9990909,0.00003124947,0.0002167742,0.0002425975,0.0001944133,0.0002240334],"domain_scores_gemma":[0.9992656,0.00009771084,0.00007564903,0.0002779239,0.0002289136,0.00005425942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003280567,0.001966795,0.001062342,0.002434888,0.0004674637,0.000254294,0.1457027,0.01775246,0.1542575,0.3572723,0.05427058,0.2642306],"study_design_scores_gemma":[0.003639787,0.000641903,0.004412881,0.0009749524,0.00003461488,0.0004532578,0.02506368,0.7070891,0.05880868,0.002071499,0.1956965,0.001113192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09392868,0.0002440589,0.9025275,0.0003903402,0.0002783995,0.0002953102,0.0000457239,0.0005509798,0.001739019],"genre_scores_gemma":[0.9906955,0.000004728321,0.008712118,0.00003953909,0.00003288072,5.25515e-8,0.0001970768,0.0002289762,0.00008909254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8967668,"threshold_uncertainty_score":0.3650856,"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."}}