{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001080288,0.0001327739,0.0001650528,0.0001129749,0.0005023371,0.0003110092,0.002206429,0.00003073947,0.00002511603],"category_scores_gemma":[0.0003088141,0.0001161323,0.00003724129,0.0003515388,0.00005781759,0.0004090197,0.002087228,0.0002399267,0.000008634212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004790367,"about_ca_system_score_gemma":0.0001103026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001058929,"about_ca_topic_score_gemma":0.00001351814,"domain_scores_codex":[0.9982479,0.00002217982,0.0003473021,0.0006495318,0.0004544812,0.0002786471],"domain_scores_gemma":[0.9989939,0.00007604657,0.0001296995,0.0004525197,0.000276257,0.00007156636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003445125,0.00005994214,0.0001106426,0.00005528531,0.00000855388,2.789099e-7,0.001921072,0.00319608,0.1669613,0.5097985,0.0001434182,0.3177105],"study_design_scores_gemma":[0.00002304554,0.0001772086,0.00002427523,0.00001957177,0.000005963802,0.000004318276,0.0002990225,0.8857565,0.1016434,0.01174586,0.0001736899,0.0001271454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4040068,0.00002229775,0.5896968,0.004771221,0.0003999123,0.0007049862,0.00001526356,0.00004973795,0.0003328893],"genre_scores_gemma":[0.9874661,0.000008254186,0.0118067,0.0003558428,0.00009217592,0.00005634427,0.00000214018,0.00001037807,0.000202058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8825604,"threshold_uncertainty_score":0.4735736,"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."}}