{"id":"W2177607365","doi":"10.1007/s10515-015-0184-4","title":"Concept extraction from business documents for software engineering projects","year":2015,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Documentation; Domain engineering; Software mining; Software engineering; Process (computing); Domain (mathematical analysis); Software; Data science; Knowledge extraction; Data mining; Domain analysis; Information extraction; Software development; Information retrieval; Software construction; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001706957,0.00124606,0.0007174063,0.01292106,0.001524791,0.002380715,0.0009696032,0.00133536,0.003770705],"category_scores_gemma":[0.01198176,0.0005525166,0.001096883,0.008538714,0.0004654198,0.003390618,0.001194009,0.00153809,0.003378985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053363,"about_ca_system_score_gemma":0.004368753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003327749,"about_ca_topic_score_gemma":0.00469067,"domain_scores_codex":[0.997726,0.0004177348,0.0003788622,0.0003834286,0.000946931,0.0001470541],"domain_scores_gemma":[0.9892325,0.006608885,0.001028449,0.0005732594,0.002244114,0.0003127124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004990101,0.0004544501,0.01150835,0.004253751,0.0001526137,0.001670148,0.002118509,0.003199823,0.0776017,0.01000892,0.04420169,0.844331],"study_design_scores_gemma":[0.0003984402,0.0009167428,0.06676876,0.002857126,0.001470827,0.007678938,0.005783625,0.1282068,0.2339272,0.04228117,0.5093444,0.0003659638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2867679,0.01157719,0.5887855,0.003280659,0.0008062004,0.003074941,0.0692646,0.01567427,0.02076873],"genre_scores_gemma":[0.2572199,0.003235259,0.6733425,0.000252925,0.0002212796,0.0009620349,0.05884686,0.0007765171,0.005142631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01292106,"threshold_uncertainty_score":0.01261425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01656998676845237,"score_gpt":0.2722598448418184,"score_spread":0.255689858073366,"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."}}