{"id":"W4411113567","doi":"10.18653/v1/2024.inlg-genchal.5","title":"pyrealb at the GEM’24 Data-to-text Task: Symbolic English Text Generation from RDF Triples","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"","keywords":"RDF; Computer science; Task (project management); Natural language processing; Text generation; Information retrieval; Artificial intelligence; 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":[0.003735083,0.001814929,0.001103712,0.001563415,0.001692171,0.002191275,0.002147165,0.001699871,0.0696078],"category_scores_gemma":[0.01292051,0.0008266888,0.001234654,0.001133599,0.001013845,0.004349185,0.00709546,0.002535432,0.0405192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009996092,"about_ca_system_score_gemma":0.00241645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004168217,"about_ca_topic_score_gemma":0.005278732,"domain_scores_codex":[0.9968218,0.001118752,0.0002231994,0.0007118011,0.0008547643,0.0002697313],"domain_scores_gemma":[0.995876,0.001535727,0.0001190769,0.001347989,0.0007192455,0.0004019823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007801678,0.0004016981,0.001471831,0.001220296,0.0001051748,0.000889493,0.001376506,0.00459971,0.02179052,0.01870761,0.6961623,0.2524947],"study_design_scores_gemma":[0.0006453831,0.0002846354,0.002704111,0.0003164835,0.00007688641,0.001157131,0.001599434,0.12038,0.07333107,0.07153686,0.7277524,0.000215617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01996657,0.0004205675,0.483867,0.00333252,0.001298154,0.00151902,0.07084227,0.3778529,0.04090096],"genre_scores_gemma":[0.1321844,0.0003098581,0.5705219,0.001242961,0.0002521609,0.001757265,0.2126347,0.05271912,0.02837763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0696078,"threshold_uncertainty_score":0.2328613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04079452227313914,"score_gpt":0.2924567835231798,"score_spread":0.2516622612500407,"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."}}