{"id":"W3032170634","doi":"10.1109/tse.2020.2998503","title":"Automatic Generation of Acceptance Test Cases From Use Case Specifications: An NLP-Based Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"European Research Council; European Commission","keywords":"Computer science; Executable; Test case; Software requirements specification; Acceptance testing; Software engineering; Test script; System under test; Conformance testing; Test Management Approach; Test (biology); Formal specification; Reliability engineering; Software; Software system; Programming language; Machine learning; Software construction","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001206519,0.0002639647,0.0002616023,0.0002534135,0.0001267761,0.0001911854,0.0005619222,0.0001057215,0.00004782086],"category_scores_gemma":[0.000688796,0.0002976944,0.0001054215,0.0009754817,0.0000307413,0.0009773287,0.000004928931,0.0003466055,0.00001885797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001102072,"about_ca_system_score_gemma":0.00009392604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008665669,"about_ca_topic_score_gemma":0.000007809109,"domain_scores_codex":[0.9982739,0.00004458911,0.0003963148,0.0005747571,0.0004156926,0.0002947636],"domain_scores_gemma":[0.9966721,0.001998691,0.00007012616,0.0008504718,0.0001402602,0.0002683754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004132359,0.0002402845,0.0003534129,0.00008537812,0.00003221177,0.000200515,0.000512941,0.9812691,0.005698903,0.0000286339,0.0000532653,0.0115212],"study_design_scores_gemma":[0.0002810891,0.0001480742,0.001001504,0.00003455068,0.00001749804,0.00009515045,0.00001945761,0.9585655,0.03950661,0.00000100542,0.00005321874,0.0002763759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2115639,0.00004470611,0.7865786,0.00003847632,0.0002265059,0.0002511514,0.0001129528,0.001183158,5.780619e-7],"genre_scores_gemma":[0.6297883,0.000004134465,0.3699757,0.00003770784,0.00006897991,0.00007500227,0.00001245392,0.00003404828,0.000003720381],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4182244,"threshold_uncertainty_score":0.9999475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1180488002370277,"score_gpt":0.2662858943771059,"score_spread":0.1482370941400782,"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."}}