{"id":"W2304545146","doi":"10.18653/v1/p16-1056","title":"Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Natural language processing; Artificial intelligence; Question answering; Sentence; Similarity (geometry); Machine translation; Knowledge base; Baseline (sea); Architecture; Artificial neural network; Information retrieval","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005086716,0.0005225139,0.0003860448,0.00009971492,0.0004492353,0.0008067745,0.002054476,0.0002643924,0.00004525376],"category_scores_gemma":[0.00007639479,0.0002762746,0.0001571603,0.0001709603,0.000105904,0.0003617305,0.001650531,0.001125322,0.00002094148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000166378,"about_ca_system_score_gemma":0.0002593535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003555035,"about_ca_topic_score_gemma":0.0003053969,"domain_scores_codex":[0.9967623,0.0003657528,0.0005777215,0.001140226,0.0005564411,0.0005976033],"domain_scores_gemma":[0.9968426,0.0002653462,0.0003762649,0.00204449,0.0002936691,0.0001776457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008688702,0.00006659132,0.002375922,0.00003616387,0.0001052578,0.00002122286,0.0006479717,0.7014176,0.00008226268,0.1013678,0.001060087,0.1928104],"study_design_scores_gemma":[0.000162149,0.00004868477,0.00044119,0.0002535,0.00002031276,0.00003548252,0.00001243992,0.9942182,0.00004334182,0.002893365,0.001384889,0.0004864643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008309376,0.0007680616,0.9800484,0.004379244,0.003735491,0.0006215838,0.00001087123,0.000612766,0.001514254],"genre_scores_gemma":[0.9074692,0.0001803986,0.08780995,0.0009555803,0.00156568,0.0002345991,0.00002638716,0.00005350011,0.001704703],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8991598,"threshold_uncertainty_score":0.9999689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02735015464353461,"score_gpt":0.2677936035776921,"score_spread":0.2404434489341574,"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."}}