Non-Autoregressive Neural Machine Translation

Sep 23, 2021 1 min read

Non-Autoregressive Transformer

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:

run_alignment_wmt_LANG.sh (runs fast_align for 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)

GitHub

Neural Network Translation

John was the first writer to have joined pythonawesome.com. He has since then inculcated very effective writing and reviewing culture at pythonawesome which rivals have found impossible to imitate.

Non-Autoregressive Neural Machine Translation

Non-Autoregressive Transformer

GitHub

John

A custom ListView with a header that displays pictures from an URL

Python partial dependence plot toolbox

Non-Autoregressive Transformer

GitHub

A custom ListView with a header that displays pictures from an URL

Python partial dependence plot toolbox

You might also like...