The goal of this project is to build a neural machine translation system and experience how recent advances have made their way. We built neural translation systems for two language pairs, Vietnamese (Vi)→English (En) and Chinese (Zh)→En.

We experimented with the following models:

(1) Recurrent neural network based encoder-decoder without attention

(2) Recurrent neural network based encoder-decoder with attention

(3) Replace the recurrent encoder with either convolutional or self-attention based encoder.

and the final models are saved in the Final Models folder. Since all team members are running their codes on different platforms: Google Colab, Google Cloud, HPC Prince, Python, so some of the jupyter notebook file doesn't have printed out results.