{"id":"W4283789759","doi":"10.1609/aaai.v36i10.21332","title":"Search and Learn: Improving Semantic Coverage for Data-to-Text Generation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Bundesministerium für Bildung und Forschung; Compute Canada; Technische Universität Kaiserslautern; Canadian Institute for Advanced Research; DeepMind; Nvidia","keywords":"Computer science; Inference; Focus (optics); Artificial intelligence; Limiting; Cover (algebra); Quality (philosophy); Training set; Language model; Natural language processing; Information retrieval; Machine learning","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":[0.002318709,0.001278608,0.001576798,0.001992038,0.000741813,0.001314774,0.002172047,0.001752076,0.004044173],"category_scores_gemma":[0.01602718,0.0006412526,0.001083218,0.001428721,0.001028343,0.005233941,0.002729187,0.001763876,0.001833465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016747,"about_ca_system_score_gemma":0.001347214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004297231,"about_ca_topic_score_gemma":0.006493174,"domain_scores_codex":[0.9981027,0.0006669054,0.0001281386,0.0005387308,0.0004309215,0.0001325753],"domain_scores_gemma":[0.9933445,0.004736823,0.0002716286,0.0009204653,0.0005624467,0.0001639928],"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":[0.001191444,0.0008376741,0.005690843,0.0007875567,0.0001864919,0.0007361576,0.001092072,0.1720637,0.02135267,0.0136704,0.03878034,0.7436107],"study_design_scores_gemma":[0.00009417775,0.00008900845,0.0003701004,0.000027605,0.00003944569,0.0001416999,0.00008373828,0.9731986,0.009907241,0.01239559,0.003632144,0.0000206847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0775306,0.001890351,0.8806764,0.0008941201,0.0001662802,0.0002857563,0.001704471,0.03311872,0.003733416],"genre_scores_gemma":[0.5979815,0.0005174453,0.3866318,0.0009121567,0.0001762575,0.000436408,0.007516514,0.002246486,0.003581328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004297231,"threshold_uncertainty_score":0.01352912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2087035607689111,"score_gpt":0.3334275307102393,"score_spread":0.1247239699413282,"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."}}