{"id":"W2963506530","doi":"10.18653/v1/p19-1602","title":"Generating Sentences from Disentangled Syntactic and Semantic Spaces","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Paraphrase; Natural language processing; Artificial intelligence; Syntax; Language model; Latent semantic analysis","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001433318,0.0002264914,0.0003088844,0.00006878415,0.00007441626,0.0008169769,0.0007290082,0.0001274078,0.00002303262],"category_scores_gemma":[0.00003718911,0.0001887892,0.00006162995,0.00005235479,0.00002194806,0.0002414059,0.002175805,0.0002849256,0.00003361778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002985724,"about_ca_system_score_gemma":0.00007966219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001778406,"about_ca_topic_score_gemma":0.0001157956,"domain_scores_codex":[0.9983191,0.00007234267,0.0002549609,0.000855386,0.0002798286,0.0002183767],"domain_scores_gemma":[0.9987102,0.0001704375,0.0001580171,0.000846424,0.00003732807,0.00007759232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002531436,0.0003824401,0.4895998,0.002467311,0.001485619,0.000505052,0.03014612,0.2058083,0.01502235,0.05418428,0.002404547,0.1979688],"study_design_scores_gemma":[0.00009016917,0.000007288704,0.000733494,0.0001522819,0.00001973178,0.000005491348,0.0002112177,0.9935177,0.0003117021,0.004673641,0.00002628549,0.0002509787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4439816,0.0006450821,0.5522928,0.0009552587,0.00116456,0.0001662268,0.000002577325,0.000135898,0.0006559396],"genre_scores_gemma":[0.8333045,0.00007394254,0.165729,0.0002194655,0.0002026442,0.000008185899,0.000005301573,0.000008741823,0.0004482416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7877094,"threshold_uncertainty_score":0.7878127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709185134092034,"score_gpt":0.2542554377898595,"score_spread":0.2271635864489392,"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."}}