donote / nmt-seq2seq

seq2seq model written in Pytorch

Sequence to sequence model for neural machine translation

requirements:

• python 3.6
• pytorch 0.3.1
• nltk
• tqdm

How to use

• To generate data set python train_test_split.py
• To train the model, simply run ./run.sh
• To test the model .run_test.sh
• To see what config options you have python main.py --help

background

• this repo tries to implement the paper Sequence to Sequence Learning with Neural Networks, some details differ from the original paper, though.
• we are using data from http://www.manythings.org/anki/

TODO

• add attention to the currently very basic model

Bug report

If you find any bugs, please feel free to send an email to [e-mail] or [e-mail] , I will try to be responsive!