AICamp1.NLP

DATA DOWNLOAD

To start this project, you need an addition data file.

First you should download data from: https://pan.baidu.com/s/1KFui9zZKjRqzFkCJH5nenw

Then unzip it,create a data dir, and put it in data directory

After you do all that , the following file should be found:

'data/segmented_train_seg_by_word.txt' 

And that means you are good to go.``

Virtual Environment Setup, Tensorflow 2.0 compatible (2020/8/1)

conda create --name nlp python=3.5
conda activate nlp
pip install -r requirements.txt

There should be three ipython notebooks in the directory:

1. text_classify_basic.ipynb is the code for RNN (Last Week,Lession 1)
2. seq2seq_basic.ipynb.ipynb is the code for machine translation (Last Week,Lession 2)
3. word2vec_basic.ipynb is the code for word embedding (Last Week,Lession 3)

Just follow the code there and you will get things running. If you encounter any problem about the code, you can either contact me directly or post an issue here.

Finally, thank you guys for playing with my code. Farewell and good luck.