{"id":"W4393775951","doi":"10.5281/zenodo.4733023","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","year":2020,"lang":"en","type":"dataset","venue":"Figshare","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 (archaeology); Software engineering; Software; Natural language; Programming language; Natural language processing; Geography; 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":[0.002550318,0.001851785,0.0008885885,0.00440493,0.001273367,0.001695831,0.002221957,0.002599583,0.008227214],"category_scores_gemma":[0.01098786,0.0003992869,0.001315734,0.003468094,0.0006128738,0.002151569,0.002747183,0.001767255,0.01099501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002154164,"about_ca_system_score_gemma":0.001758106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02815765,"about_ca_topic_score_gemma":0.05897057,"domain_scores_codex":[0.9970589,0.0008563319,0.000312454,0.0007582676,0.0007480978,0.0002659419],"domain_scores_gemma":[0.9936472,0.002647304,0.0004752026,0.001164603,0.001454444,0.0006111978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001260864,0.0009211766,0.01600078,0.003121135,0.0002725165,0.0002335899,0.0007670438,0.003807778,0.002010692,0.002888799,0.9302225,0.0384931],"study_design_scores_gemma":[0.001034699,0.0006064814,0.1199045,0.0009573424,0.0002893256,0.0006830318,0.002544843,0.02314656,0.005321098,0.00465959,0.8406153,0.00023728],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02943677,0.000817332,0.001773996,0.0005998397,0.0001512077,0.0002840237,0.9581711,0.002639068,0.006126632],"genre_scores_gemma":[0.008450671,0.00007516856,0.001880457,0.0001027919,0.00001202102,0.0002789664,0.9880336,0.00006468555,0.001101565],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02815765,"threshold_uncertainty_score":0.05598754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09965953655803168,"score_gpt":0.3454661325239714,"score_spread":0.2458065959659397,"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."}}