@misc{dai2019transformer, title={Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context}, author={Zihang Dai and Zhilin Yang and Yiming Yang and William W. Cohen and Jaime Carbonell and Quoc V. Le and Ruslan Salakhutdinov}, year={2019}, eprint={1901.02860}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1901.02860} }