Neural Machine Translation

Neural Machine Translation Project for NLP Class at NYU MS in Data Science

Project Overview

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

The Models

• Recurrent neural network based encoder-decoder without attention
• Recurrent neural network based encoder-decoder with attention
• Convolutional or self-attention based encoder.
• Self-attention translation system
• Multilingual translation system

Requirements

To be able to run the notebooks you should install the following packages:

• spacy
• underthesea
• jieba
• pdb
• sacrebleu

All of them can be downloaded using the commands below

pip install spacy && python -m spacy download en
pip install underthesea
pip install jieba
pip install pdb
pip3 install sacrebleu