{"id":"W4287671547","doi":"10.5281/zenodo.3524521","title":"A Comparison of Natural Language Understanding Services for Software Bots","year":2020,"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 (archaeology); Natural language; Software; Software engineering; Natural language processing; Programming language; History","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":[0.004071214,0.001117151,0.0009746797,0.002107316,0.0007678914,0.00156279,0.001240711,0.002933611,0.01094789],"category_scores_gemma":[0.02537972,0.0003578996,0.0006467865,0.001138103,0.0005814697,0.005528869,0.001607412,0.001707353,0.004607925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009086109,"about_ca_system_score_gemma":0.001857864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01585458,"about_ca_topic_score_gemma":0.01685703,"domain_scores_codex":[0.9963713,0.001095101,0.0004324773,0.000711265,0.0009014971,0.0004884296],"domain_scores_gemma":[0.969079,0.02281534,0.0007393147,0.002537641,0.003413649,0.001415186],"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":[0.02679823,0.005751852,0.04669196,0.005056082,0.0007525031,0.001724981,0.00790543,0.03578875,0.1025184,0.007232312,0.08398283,0.6757967],"study_design_scores_gemma":[0.001445193,0.01225475,0.1547323,0.0006050721,0.000779446,0.002211407,0.01218919,0.6378977,0.0856327,0.01366901,0.07808081,0.0005022475],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9290393,0.001358921,0.01972137,0.0008513127,0.0002675287,0.000509012,0.009374613,0.02009677,0.01878119],"genre_scores_gemma":[0.954458,0.0004205861,0.01674401,0.0002746809,0.0000506728,0.0002073493,0.01963235,0.001020116,0.007192231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01585458,"threshold_uncertainty_score":0.03662431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08525610431880891,"score_gpt":0.3161836927182475,"score_spread":0.2309275883994386,"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."}}