Fast Structured Decoding for Sequence Models

方法与贡献

为非自回归序列模型加入近似一阶 CRF 推断和动态转移。

一阶结构化解码的参考工作；Cascaded Text Generation 发展了高阶级联和共享的 Markov Transformer 势函数。

结合主题阅读

结构化解码：高阶 CRF、扩散语言模型与候选格 →

引用

Zhiqing Sun, Zhuohan Li, Haoqing Wang, Di He, Zi Lin, Zhi-Hong Deng. Fast Structured Decoding for Sequence Models. NeurIPS 2019.

@inproceedings{sun2019fast,
  title = {{Fast Structured Decoding for Sequence Models}},
  author = {Sun, Zhiqing and Li, Zhuohan and Wang, Haoqing and He, Di and Lin, Zi and Deng, Zhi-Hong},
  year = {2019},
  booktitle = {NeurIPS 2019},
  url = {https://proceedings.neurips.cc/paper_files/paper/2019/hash/74563ba21a90da13dacf2a73e3ddefa7-Abstract.html},
  eprint = {1910.11555},
  archivePrefix = {arXiv}
}