{"id":"W3111275476","doi":"10.1109/tse.2021.3078384","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Chatbot; Computer science; IBM; Natural language understanding; Natural language; Task (project management); Software; Data science; Artificial intelligence; Software engineering; World Wide Web; Natural language processing; Programming language; Engineering","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":[0.01049906,0.001591208,0.001183028,0.005986601,0.001140938,0.002983351,0.001597741,0.002292957,0.002144545],"category_scores_gemma":[0.03641912,0.0005395221,0.00133641,0.002034589,0.0009088469,0.00806092,0.003560568,0.002228377,0.002508084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001660591,"about_ca_system_score_gemma":0.001672878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00555375,"about_ca_topic_score_gemma":0.008249082,"domain_scores_codex":[0.9900748,0.004554547,0.001057245,0.001935411,0.001935623,0.000442288],"domain_scores_gemma":[0.9607784,0.02946869,0.001669708,0.002448771,0.003931113,0.001703322],"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":[0.01005653,0.003093421,0.0521597,0.007643786,0.0009171618,0.001205052,0.01802421,0.0212463,0.04936204,0.008889765,0.04492052,0.7824815],"study_design_scores_gemma":[0.001500962,0.008492857,0.2226238,0.001981394,0.0009300864,0.002338236,0.01768725,0.5328187,0.05538917,0.01716746,0.1379408,0.001129293],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8653842,0.007063255,0.06861119,0.001652006,0.0004967208,0.001297876,0.006637066,0.03304467,0.01581299],"genre_scores_gemma":[0.8310165,0.00189142,0.1199246,0.0006229556,0.0001803138,0.001273126,0.03761604,0.001665322,0.005809723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01049906,"threshold_uncertainty_score":0.055525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0374386258312366,"score_gpt":0.2990128889211052,"score_spread":0.2615742630898686,"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."}}