OpenNMT-py | Open Source Neural Machine Translation in PyTorch | Machine Learning library

@inproceedings{ruiter2019self-supervised,
  title={Self-Supervised Neural Machine Translation},
  author={Ruiter, Dana and Espa{\~{n}}a-Bonet, Cristina and van Genabith, Josef},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association  

@inproceedings{zekangli2018incremental,
 author = {Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, Jie Zhou},
 booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
 title = {Incremental Transf  

train_src: train_data.tok.srcmt
train_tgt: train_data.tok.pe

valid_src: dev.tok.srcmt
valid_tgt: dev.tok.pe

save_data: prep-data

src_vocab_size: 200000
tgt_vocab_size: 200000

shard_size: 100000

bert_src: bert-base-multilingual-cased
bert_tgt: be  

"""
An original implementation of sparsemax (Martins & Astudillo, 2016) is available at
https://github.com/OpenNMT/OpenNMT-py/blob/master/onmt/modules/sparse_activations.py.
See `From Softmax to Sparsemax: A Sparse Model of Attention and Multi-La  

"""
.. _model-transformer:

Transformer as a Graph Neural Network
======================================

**Author**: Zihao Ye, Jinjing Zhou, Qipeng Guo, Quan Gan, Zheng Zhang

.. warning::

    The tutorial aims at gaining insights into the paper, w  

pip install --upgrade OpenNMT-py==2.0.0rc1;
wget https://s3.amazonaws.com/opennmt-trainingdata/toy-ende.tar.gz;
tar xf toy-ende.tar.gz;
echo '## Where the samples will be written
save_data: toy-ende/run/example
## Where the vocab(s) will b

Mon Feb 10 16:10:25 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.87.01    Driver Version: 418.87.01    CUDA Version: 10.1     |
|-------------------------------+--------------

$ git clone https://github.com/chirlu/sox/tree/master/lpc10 sox2
$ cp -R sox2/lpc10 sox

Start window -> open local folder -> sox/lpc10
(it reads CMakeLists.txt automatically)
Build->build All

for name, param in self.encoder.named_parameters():
    param.requires_grad = False

class Net(nn.Module):
    def __init__(self, params):
        super(Net, self).__init__()

        self.encoder = TransformerEncod