Code release for Non-Autoregressive Neural Machine Translation by Jiatao Gu, James Bradbury, Caiming Xiong, Victor O.K. Li, and Richard Socher.
Requires PyTorch 0.3, torchtext 0.2.1, and SpaCy.
The pipeline for training a NAT model for a given language pair includes:
fast_alignfor alignment supervision)
run_LANG.sh(trains an autoregressive model)
run_LANG_decode.sh(produces the distillation corpus for training the NAT)
run_LANG_fast.sh(trains the NAT model)
run_LANG_fine.sh(fine-tunes the NAT model)