mirror of
https://gitee.com/fastnlp/fastNLP.git
synced 2024-12-05 05:38:31 +08:00
501ffb26c5
- see test_fastNLP.py - update interpret_word_seg_results in fastnlp.py - delete useless data to increase git clone speed |
||
---|---|---|
.. | ||
__init__.py | ||
evaluate.py | ||
model.py | ||
preprocess.py | ||
README.md | ||
train.py |
Introduction
This is the implementation of Hierarchical Attention Networks for Document Classification paper in PyTorch.
- Dataset is 600k documents extracted from Yelp 2018 customer reviews
- Use NLTK and Stanford CoreNLP to tokenize documents and sentences
- Both CPU & GPU support
- The best accuracy is 71%, reaching the same performance in the paper
Requirement
- python 3.6
- pytorch = 0.3.0
- numpy
- gensim
- nltk
- coreNLP
Parameters
According to the paper and experiment, I set model parameters:
word embedding dimension | GRU hidden size | GRU layer | word/sentence context vector dimension |
---|---|---|---|
200 | 50 | 1 | 100 |
And the training parameters:
Epoch | learning rate | momentum | batch size |
---|---|---|---|
3 | 0.01 | 0.9 | 64 |
Run
- Prepare dataset. Download the data set, and unzip the custom reviews as a file. Use preprocess.py to transform file into data set foe model input.
- Train the model. Word enbedding of train data in 'yelp.word2vec'. The model will trained and autosaved in 'model.dict'
python train
- Test the model.
python evaluate