@inproceedings{counterfactualoffpolicytrainingforneural, title = {Counterfactual Off-Policy Training for Neural Dialogue Generation}, author = {Qingfu Zhu and Wei-Nan Zhang and Ting Liu and William Yang Wang}, year = {2020}, booktitle = {EMNLP 2020 11}, url = {https://aclanthology.org/2020.emnlp-main.276}, }