GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection.

Wanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu, Zheng Cao, Dermot Liu, Peng Jiang, Min Yang, Fei Huang, Luo Si, Jian Sun, Yongbin Li

Browse the full AAAI paper archive.