A Batch Normalized Inference Network Keeps the KL Vanishing Away Qile Zhu author Wei Bi author Xiaojiang Liu author Xiyao Ma author Xiaolin Li author Dapeng Wu author 2020-07 text Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Dan Jurafsky editor Joyce Chai editor Natalie Schluter editor Joel Tetreault editor Association for Computational Linguistics Online conference publication zhu-etal-2020-batch 10.18653/v1/2020.acl-main.235 https://aclanthology.org/2020.acl-main.235/ 2020-07 2636 2649