https://github.com/indiejoseph/cnn-text-classification-tf-chinese

CNN for Chinese Text Classification in Tensorflow
https://github.com/indiejoseph/cnn-text-classification-tf-chinese

chinese cnn convolutional-neural-networks deep-learning nlp tensorflow text-classification

Last synced: about 2 months ago
JSON representation

CNN for Chinese Text Classification in Tensorflow

• Host: GitHub
• URL: https://github.com/indiejoseph/cnn-text-classification-tf-chinese
• Owner: indiejoseph
• Archived: true
• Created: 2016-03-09T03:41:17.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2018-01-23T03:20:23.000Z (almost 7 years ago)
• Last Synced: 2024-05-23T04:46:51.470Z (8 months ago)
• Topics: chinese, cnn, convolutional-neural-networks, deep-learning, nlp, tensorflow, text-classification
• Language: Python
• Size: 3.49 MB
• Stars: 237
• Watchers: 27
• Forks: 109
• Open Issues: 9
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## CNN for Chinese Text Classification in Tensorflow

Sentiment classification forked from [dennybritz/cnn-text-classification-tf](https://github.com/dennybritz/cnn-text-classification-tf), make the data helper supports Chinese language and modified the embedding from word-level to character-level, though that increased vocabulary size, and also i've implemented the [Character-Aware Neural Language Models](http://arxiv.org/pdf/1508.06615v4.pdf) network structure which CNN + Highway network to improve the performance, this version can achieve an accuracy of 98% with the Chinese corpus

**[This code belongs to the "Implementing a CNN for Text Classification in Tensorflow" blog post.](http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/)**

It is slightly simplified implementation of Kim's [Convolutional Neural Networks for Sentence Classification](http://arxiv.org/abs/1408.5882) paper in Tensorflow.

## Requirements

- Python 2.7

- Tensorflow 0.9.0

- Numpy

## Running

Print parameters:

```bash

./train.py --help

```

```

optional arguments:

  -h, --help            show this help message and exit

  --embedding_dim EMBEDDING_DIM

                        Dimensionality of character embedding (default: 128)

  --filter_sizes FILTER_SIZES

                        Comma-separated filter sizes (default: '1,2,3,4,5,6,8')

  --num_filters NUM_FILTERS

                        Number of filters per filter size (default: '50,100,150,150,200,200,200')

  --l2_reg_lambda L2_REG_LAMBDA

                        L2 regularizaion lambda (default: 0.0)                        

  --dropout_keep_prob DROPOUT_KEEP_PROB

                        Dropout keep probability (default: 0.5)

  --batch_size BATCH_SIZE

                        Batch Size (default: 32)

  --num_epochs NUM_EPOCHS

                        Number of training epochs (default: 100)

  --evaluate_every EVALUATE_EVERY

                        Evaluate model on dev set after this many steps

                        (default: 100)

  --checkpoint_every CHECKPOINT_EVERY

                        Save model after this many steps (default: 100)

  --allow_soft_placement ALLOW_SOFT_PLACEMENT

                        Allow device soft device placement

  --noallow_soft_placement

  --log_device_placement LOG_DEVICE_PLACEMENT

                        Log placement of ops on devices

  --nolog_device_placement

```

Train:

```bash

./train.py

```

## References

- [Convolutional Neural Networks for Sentence Classification](http://arxiv.org/abs/1408.5882)

- [A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification](http://arxiv.org/abs/1510.03820)