{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002022307,0.0003838517,0.0003924462,0.0003221531,0.00008048632,0.0002249323,0.0007526052,0.0001860444,0.000003804366],"category_scores_gemma":[0.001990605,0.0004180071,0.0001064798,0.001007827,0.00001464804,0.001759675,0.0002103357,0.0002035087,0.00001881096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003148759,"about_ca_system_score_gemma":0.0001086504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007763292,"about_ca_topic_score_gemma":0.000002435319,"domain_scores_codex":[0.9979934,0.00001706728,0.0004195238,0.0006257806,0.0004008768,0.0005433232],"domain_scores_gemma":[0.9981729,0.0003824842,0.0001577574,0.0006714963,0.0004083801,0.0002069751],"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":[0.00002939391,0.0002050218,0.004121452,0.0002662922,0.0005107497,0.0001396282,0.002563071,0.9423791,0.01172648,0.001805649,0.008071024,0.02818213],"study_design_scores_gemma":[0.0008843927,0.00006965903,0.00415256,0.0002329209,0.00005281669,0.00002401075,0.00002268022,0.9645466,0.02147765,0.0003019234,0.007369195,0.0008656033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02166442,0.0003307968,0.9592842,0.00002997297,0.0007589163,0.0004572259,0.00001890701,0.01745193,0.000003561087],"genre_scores_gemma":[0.2430213,0.000006747086,0.7563935,0.00003497026,0.0001379548,0.0002072986,0.000091367,0.00006959172,0.00003729376],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2213569,"threshold_uncertainty_score":0.9998271,"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."}}