{"id":"W4284689801","doi":"10.1145/3510003.3510157","title":"Automated handling of anaphoric ambiguity in requirements","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg","keywords":"Ambiguity; Computer science; Anaphora (linguistics); Artificial intelligence; Natural language processing; Coreference; Natural language; Natural language understanding; Interpretation (philosophy); Ambiguity resolution; Automation; Machine translation; Feature (linguistics); Resolution (logic); Machine learning; Programming language; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005869314,0.0001435837,0.0001936794,0.0004687688,0.00005903365,0.00003881686,0.002209855,0.00003374592,0.00002854507],"category_scores_gemma":[0.001491924,0.0001373494,0.00007385014,0.0009008317,0.00002518874,0.0002882736,0.001022207,0.0002962898,0.000001326417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000272049,"about_ca_system_score_gemma":0.00007843559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003593033,"about_ca_topic_score_gemma":5.991618e-7,"domain_scores_codex":[0.9981022,0.000008434251,0.0003774856,0.0002908226,0.000974531,0.0002465523],"domain_scores_gemma":[0.9991202,0.0001443649,0.0001793295,0.000192966,0.0003188528,0.00004428763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001335494,0.0006466878,0.5078922,0.000624101,0.0002870795,0.00001491512,0.003443182,0.2067316,0.08699,0.1872828,0.001315193,0.004638712],"study_design_scores_gemma":[0.0008310915,0.0002055104,0.1646388,0.0004654613,0.00000563851,0.00001819697,0.0001158526,0.7915292,0.04053527,0.0009612241,0.0003283464,0.0003652888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859356,0.00004228394,0.01176618,0.0002255992,0.00104325,0.0002428403,0.00001585692,0.0004761871,0.0002521676],"genre_scores_gemma":[0.9895804,0.000007929102,0.01024671,0.0000166713,0.00001969511,0.00005628457,0.000001496083,0.00001511264,0.00005573183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5847977,"threshold_uncertainty_score":0.5600945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0372657344313989,"score_gpt":0.286035888320043,"score_spread":0.248770153888644,"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."}}