{"id":"W2752442988","doi":"10.1609/aaai.v32i1.11947","title":"Order-Planning Neural Text Generation From Structured Data","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Dialog box; Table (database); Natural language generation; Natural language processing; Artificial neural network; Artificial intelligence; Text generation; Encoder; NIST; Language model; Order (exchange); Component (thermodynamics); Natural language; Machine learning; Data mining","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":[0.0009595777,0.0009083248,0.0006136055,0.0008690262,0.0004027026,0.0006145742,0.001486357,0.0008959933,0.003415649],"category_scores_gemma":[0.004244279,0.0003642102,0.0006768184,0.0008681547,0.0004743912,0.001752438,0.0007973885,0.001238322,0.001041031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009327818,"about_ca_system_score_gemma":0.0008620327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006635321,"about_ca_topic_score_gemma":0.01240841,"domain_scores_codex":[0.9995782,0.0001060707,0.00002671892,0.0001761701,0.00007455358,0.00003826083],"domain_scores_gemma":[0.9978964,0.001405416,0.0000993765,0.0002693223,0.0002592323,0.00007028554],"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":[0.0003836339,0.0003581419,0.001938088,0.0002907754,0.0000793118,0.0003342181,0.0003012955,0.403487,0.01346808,0.009558996,0.01745425,0.5523462],"study_design_scores_gemma":[0.00002614345,0.00002709562,0.0001377523,0.000004600676,0.000009095009,0.0000237147,0.00001787018,0.989096,0.004076465,0.005788977,0.0007869081,0.000005471062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1253316,0.0009799645,0.848022,0.0008335774,0.0002724808,0.0004258447,0.001550321,0.01574037,0.006843796],"genre_scores_gemma":[0.6625438,0.000338817,0.3215569,0.0004039254,0.0001284267,0.0004574045,0.004656025,0.0005155436,0.009399149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006635321,"threshold_uncertainty_score":0.01319337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2217427354035592,"score_gpt":0.3408933794995286,"score_spread":0.1191506440959695,"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."}}