{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005489571,0.001426892,0.0008518225,0.002736513,0.00101088,0.002247922,0.001625316,0.001528475,0.002427839],"category_scores_gemma":[0.03290972,0.0009327004,0.001555833,0.001640236,0.001037595,0.0043902,0.003127659,0.002357408,0.001495506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001029992,"about_ca_system_score_gemma":0.003012597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002268629,"about_ca_topic_score_gemma":0.003828986,"domain_scores_codex":[0.9878026,0.005730532,0.0007252051,0.00142402,0.003987744,0.0003298457],"domain_scores_gemma":[0.9751846,0.01481944,0.002546848,0.004091058,0.003117192,0.0002409635],"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":[0.0002431946,0.000413246,0.007119377,0.001286557,0.0001578377,0.0009468944,0.00272164,0.08308984,0.04058652,0.02310191,0.01537163,0.8249614],"study_design_scores_gemma":[0.00007932002,0.0001864173,0.004990766,0.0002014611,0.0001150772,0.001671576,0.001647072,0.82472,0.05791468,0.06565583,0.04269265,0.0001252541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0644329,0.0004205688,0.9142296,0.001278176,0.000039968,0.0004678804,0.000686894,0.01308372,0.005360255],"genre_scores_gemma":[0.3045946,0.0002317942,0.6903859,0.0003677434,0.00003361035,0.0001904831,0.001769696,0.0006348733,0.001791301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005489571,"threshold_uncertainty_score":0.02903199,"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."}}