Hi, this is an implementation of the paper "Exploring Recombination for Efficient Decoding of Neural Machine Translation" in EMNLP 2018.
Please refer to the paper for more details: paper bib
Fisrt, we need a NMT model, use train.py to get it. Please refer to examples/train.sh as an example for the training of En-De and Zh-En models.
Next, use the trained models for NMT decoding with test.py, see examples/test.sh as the reference.
Please refer to examples/options.md for descriptions about cmd options.
This code is implemented in python3 with the DyNet toolkit. Please use a relatively newer version of DyNet, we tested it with the version of this commit.