Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dongjun-Lee/text-classification-models-tf
Tensorflow implementations of Text Classification Models.
https://github.com/dongjun-Lee/text-classification-models-tf
tensorflow text-classification
Last synced: about 2 months ago
JSON representation
Tensorflow implementations of Text Classification Models.
- Host: GitHub
- URL: https://github.com/dongjun-Lee/text-classification-models-tf
- Owner: dongjun-Lee
- Created: 2018-07-15T07:11:07.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2022-11-19T02:12:06.000Z (about 2 years ago)
- Last Synced: 2024-08-08T23:22:51.341Z (6 months ago)
- Topics: tensorflow, text-classification
- Language: Python
- Size: 10.7 KB
- Stars: 505
- Watchers: 19
- Forks: 166
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Text Classification Models with Tensorflow
Tensorflow implementation of Text Classification Models.
Implemented Models:
1. Word-level CNN [[paper](https://arxiv.org/abs/1408.5882)]
2. Character-level CNN [[paper](https://arxiv.org/abs/1509.01626)]
3. Very Deep CNN [[paper](https://arxiv.org/abs/1606.01781)]
4. Word-level Bidirectional RNN
5. Attention-Based Bidirectional RNN [[paper](http://www.aclweb.org/anthology/P16-2034)]
6. RCNN [[paper](https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9745/9552)]
Semi-supervised text classification(Transfer learning) models are implemented at [[dongjun-Lee/transfer-learning-text-tf]](https://github.com/dongjun-Lee/transfer-learning-text-tf).
## Requirements
- Python3
- Tensorflow
- pip install -r requirements.txt
## Usage
### Train
To train classification models for dbpedia dataset,
```
$ python train.py --model=""
```
(\: word_cnn | char_cnn | vd_cnn | word_rnn | att_rnn | rcnn)
### Test
To test classification accuracy for test data after training,
```
$ python test.py --model=""
```
### Sample Test Results
Trained and tested with dbpedia dataset. (```dbpedia_csv/train.csv```, ```dbpedia_csv/test.csv```)
Model | WordCNN | CharCNN | VDCNN | WordRNN | AttentionRNN | RCNN | *SA-LSTM | *LM-LSTM |
:---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
Accuracy | 98.42% | 98.05% | 97.60% | 98.57% | 98.61% | 98.68% | 98.88% | 98.86% |
(SA-LSTM and LM-LSTM are implemented at [[dongjun-Lee/transfer-learning-text-tf]](https://github.com/dongjun-Lee/transfer-learning-text-tf).)
## Models
### 1. Word-level CNN
Implementation of [Convolutional Neural Networks for Sentence Classification](https://arxiv.org/abs/1408.5882).
### 2. Char-level CNN
Implementation of [Character-level Convolutional Networks for Text Classification](https://arxiv.org/abs/1509.01626).
### 3. Very Deep CNN (VDCNN)
Implementation of [Very Deep Convolutional Networks for Text Classification](https://arxiv.org/abs/1606.01781).
### 4. Word-level Bi-RNN
Bi-directional RNN for Text Classification.
1. Embedding layer
2. Bidirectional RNN layer
3. Concat all the outputs from RNN layer
4. Fully-connected layer
### 5. Attention-Based Bi-RNN
Implementation of [Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification](http://www.aclweb.org/anthology/P16-2034).
### 6. RCNN
Implementation of [Recurrent Convolutional Neural Networks for Text Classification](https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9745/9552).
## References
- [dennybritz/cnn-text-classification-tf](https://github.com/dennybritz/cnn-text-classification-tf)
- [zonetrooper32/VDCNN](https://github.com/zonetrooper32/VDCNN)