{"id":"W4381489754","doi":"10.1145/3594778.3594877","title":"EAGER: Explainable Question Answering Using Knowledge Graphs","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; York University; University of Waterloo; Ontario Tech University","funders":"","keywords":"Question answering; Computer science; Knowledge graph; Modular design; Pipeline (software); Graph; Natural language; Artificial intelligence; Natural language processing; Information retrieval; Theoretical computer science; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002637352,0.001616287,0.0006046869,0.002996919,0.000777516,0.003171665,0.002542771,0.00237571,0.03182109],"category_scores_gemma":[0.01553862,0.0008509982,0.002152999,0.001447664,0.001187464,0.007071676,0.003832391,0.002874591,0.009000945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009888249,"about_ca_system_score_gemma":0.001304919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00301159,"about_ca_topic_score_gemma":0.006548896,"domain_scores_codex":[0.9977282,0.000946325,0.0001447021,0.0006049089,0.0004571054,0.0001188106],"domain_scores_gemma":[0.99203,0.006017923,0.000285431,0.001057172,0.0004588674,0.000150509],"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":[0.0003927108,0.0003988546,0.00227512,0.002228971,0.0003034845,0.001134194,0.002781312,0.03815889,0.01708199,0.2332907,0.1458406,0.5561133],"study_design_scores_gemma":[0.0001654689,0.0001134738,0.0008287175,0.0003291717,0.0001110873,0.0006275729,0.000648839,0.3216361,0.02218747,0.4038449,0.249369,0.0001383353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002667373,0.0002681854,0.9316815,0.0008176686,0.00009788223,0.0002698314,0.003886177,0.05590592,0.004405526],"genre_scores_gemma":[0.0851561,0.0006623096,0.8862188,0.0007993093,0.0001056268,0.0004749362,0.01610757,0.004183984,0.00629137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03182109,"threshold_uncertainty_score":0.1064522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0500733304563139,"score_gpt":0.3037788247930684,"score_spread":0.2537054943367545,"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."}}