ResearchBenchmarksDialog Response Generation on FEWSHOTWOZ TV 1.0 (test)Follow32.95BLEUSC-GPT21.967624.818827.6730.5212Feb 27, 2020Evaluation ResultsMethodMethodLinksBLEUERRSC-GPTbackbone=GPT2-Medium,...backbone=GPT2-Medium, number_of_parameters=345M2020.0232.953.38GPT-2backbone=GPT2-Medium,...backbone=GPT2-Medium, number_of_parameters=345M2020.0228.479.44SC-LSTMmodel_type=Semanticall...model_type=Semantically Conditioned LSTM2020.0222.3964.62