{"id":"W4402124327","doi":"10.1109/access.2024.3453215","title":"A Comprehensive Evaluation of Neural SPARQL Query Generation From Natural Language Questions","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; SPARQL; RDF query language; Natural language generation; Query language; Natural language; Information retrieval; Natural language processing; Web search query; Artificial intelligence; Natural language user interface; Web query classification; Search engine; Semantic Web; RDF","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":[0.007141809,0.001378686,0.0009814958,0.001036633,0.0006709999,0.001160888,0.002133193,0.001449757,0.004951927],"category_scores_gemma":[0.02488929,0.0004412359,0.0007560898,0.001389615,0.0006417588,0.002849247,0.001338391,0.001575366,0.001808367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002030839,"about_ca_system_score_gemma":0.001784554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01653647,"about_ca_topic_score_gemma":0.01544875,"domain_scores_codex":[0.9954844,0.002065586,0.0003942871,0.0007869368,0.001104677,0.0001640448],"domain_scores_gemma":[0.9881896,0.008484288,0.0002420742,0.001221425,0.001630238,0.0002323553],"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":[0.00299477,0.00236944,0.009600106,0.004633837,0.0008602295,0.0005130719,0.000860238,0.250101,0.02337083,0.004337948,0.04100829,0.6593503],"study_design_scores_gemma":[0.0003506437,0.001312269,0.004922482,0.0001571342,0.0001722516,0.0003145696,0.0004178647,0.948577,0.0273026,0.003262844,0.01314113,0.00006927332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7669035,0.009876964,0.134768,0.002501351,0.00068489,0.001619856,0.01029384,0.05020817,0.02314342],"genre_scores_gemma":[0.8221349,0.002296069,0.1375917,0.000835324,0.0001138671,0.0005116828,0.02913109,0.001459268,0.005926137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01653647,"threshold_uncertainty_score":0.03776997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1106845422785603,"score_gpt":0.3852054805728277,"score_spread":0.2745209382942674,"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."}}