爱丁堡大学神经机器翻译系统 nematus 使用笔记

*博客地址：http://blog.csdn.net/wangxinginnlp/article/details/64921476

*由于没有step by step instruction，被代码搞晕了些，写个说明文档以备后用。[要注意，红色字都是坑]

代码准备：

nematus https://github.com/rsennrich/nematus

subword-nmt  https://github.com/rsennrich/subword-nmt

数据准备：

nematus中自带了1000句对英德双语语料（En-De）

实验环境：

nematus里面写了需要配置：

Nematus requires the following packages:

• Python >= 2.7
• numpy
• Theano >= 0.7 (and its dependencies).

we recommend executing the following command in a Python virtual environment: pip install numpy numexpr cython tables theano

the following packages are optional, but highly recommended

• CUDA >= 7 (only GPU training is sufficiently fast)
• cuDNN >= 4 (speeds up training substantially)

you can run Nematus locally. To install it, execute python setup.py install

实验疑点：

1.  为什么有多个source dictionaries？支持Linguistic Input Features，每个Feauture一个dictionary？

nematus支持传入多个source dictionaries

nmt.py中接收source dictionary代码：

train = TextIterator(datasets[0], datasets[1],
                         dictionaries[:-1], dictionaries[-1],

  ....)