{"id":"W4388132093","doi":"10.1007/978-3-031-47240-4_26","title":"Assessing the Generalization Capabilities of Neural Machine Translation Models for SPARQL Query Generation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Artificial intelligence; SPARQL; Machine translation; Machine learning; Generalization; Training set; Natural language processing; Information retrieval; RDF; Semantic Web","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":[0.007546666,0.000976923,0.0006809592,0.001073997,0.0004399182,0.00126473,0.001136095,0.001882573,0.002286335],"category_scores_gemma":[0.03209979,0.0004047712,0.0007397055,0.001317018,0.000601189,0.002969136,0.00106871,0.001628436,0.0007642585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001326867,"about_ca_system_score_gemma":0.0008729031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01413792,"about_ca_topic_score_gemma":0.01067707,"domain_scores_codex":[0.9976315,0.001288836,0.0002094175,0.0004359796,0.0003094232,0.0001247293],"domain_scores_gemma":[0.9663684,0.02913932,0.0007182751,0.002044989,0.001460833,0.0002681999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002537125,0.0007161058,0.0151218,0.0004599571,0.0005695599,0.0001724292,0.0003399924,0.683782,0.00645235,0.002967747,0.006454572,0.2804263],"study_design_scores_gemma":[0.00004732958,0.0002441099,0.001980971,0.00001755443,0.00006436933,0.00003515485,0.00006791485,0.9925302,0.00247271,0.002282907,0.0002412045,0.00001559867],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9383656,0.002895198,0.04802936,0.001331484,0.0001887509,0.0001234355,0.001348125,0.00241304,0.005304911],"genre_scores_gemma":[0.9812223,0.000456297,0.01496156,0.0001383365,0.00006615787,0.00005613745,0.002010057,0.0001092669,0.0009797089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01413792,"threshold_uncertainty_score":0.03991103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0573266660516145,"score_gpt":0.3083427911285103,"score_spread":0.2510161250768957,"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."}}