Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change Hongfei Xu author Josef van Genabith author Deyi Xiong author Qiuhui Liu 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 xu-etal-2020-dynamically 10.18653/v1/2020.acl-main.323 https://aclanthology.org/2020.acl-main.323/ 2020-07 3519 3524