This repository contains the code in both PyTorch and TensorFlow for our paper
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
Zihang Dai*, Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov (*: equal contribution)
Preprint 2018
- The source code is in the
tf/folder, supporting (1) single-node multi-gpu training, and (2) multi-host TPU training. - Besides the source code, we also provide pretrained "TensorFlow" models with state-of-the-art (SoTA) performances reported in the paper.
- Please refer to
tf/README.mdfor details.
- The source code is in the
pytorch/folder, supporting single-node multi-gpu training via the modulenn.DataParallel. - Please refer to
pytorch/README.mdfor details.
Transformer-XL achieves new state-of-the-art results on multiple language modeling benchmarks. Transformer-XL is also the first to break through the 1.0 barrier on char-level language modeling. Below is a summary.
| Method | enwiki8 | text8 | One Billion Word | WT-103 | PTB (w/o finetuning) |
|---|---|---|---|---|---|
| Previous Best | 1.06 | 1.13 | 23.7 | 20.5 | 55.5 |
| Transformer-XL | 0.99 | 1.08 | 21.8 | 18.3 | 54.5 |
A large portion of the getdata.sh script comes from the awd-lstm repo. Happy Language Modeling :)