{"id":"W2976855657","doi":"10.1007/s10791-019-09364-x","title":"ReBoost: a retrieval-boosted sequence-to-sequence model for neural response generation","year":2019,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Conversation; Sequence (biology); Process (computing); Artificial intelligence; Natural language generation; Artificial neural network; Language model; Natural language processing; Recurrent neural network; Machine learning; Natural language; Programming language; Linguistics","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":[0.001450704,0.0002161703,0.0002216691,0.0003561389,0.0001814812,0.0004467911,0.0008575641,0.0001681538,0.00001466723],"category_scores_gemma":[0.0008624003,0.0002170535,0.0001017879,0.0007054896,0.00002418436,0.004090133,0.000158905,0.0001911788,0.0003587093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002853267,"about_ca_system_score_gemma":0.0003951143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006716341,"about_ca_topic_score_gemma":0.000001007991,"domain_scores_codex":[0.9976791,0.00009269248,0.0007370894,0.0003689482,0.0006877419,0.0004344753],"domain_scores_gemma":[0.9978774,0.0001736581,0.0002702385,0.0009075433,0.0005895459,0.0001815843],"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":[0.003132684,0.00003063073,0.0001263696,0.0001189673,0.00002785051,0.000004178572,0.0109792,0.6805344,0.2461183,0.03273423,0.001555016,0.0246382],"study_design_scores_gemma":[0.0007968033,0.0002418384,0.00005211249,0.00002119904,0.000004531062,0.00001968601,0.0000295893,0.9821163,0.01371604,0.00053965,0.002188241,0.0002740068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4081828,0.000006275698,0.5883753,0.001513113,0.0005336319,0.0009094819,0.00003032443,0.0001999773,0.000249058],"genre_scores_gemma":[0.9350578,0.000002122336,0.06088006,0.002997816,0.00009069626,0.00002005989,0.00005538219,0.00001238719,0.0008836364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5274953,"threshold_uncertainty_score":0.8851187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06926171490965688,"score_gpt":0.2995985784680832,"score_spread":0.2303368635584264,"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."}}