29 citations · 29 across the 2 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020
Semantics-Preserving Adversarial Training
Wonseok Lee, Hanbit Lee, Sang-goo Lee
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this pape…
cs.CL2020
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
Kang Min Yoo, Hanbit Lee, Franck Dernoncourt +3
Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. In this…