https://github.com/carpedm20/variational-text-tensorflow

TensorFlow implementation of Neural Variational Inference for Text Processing
https://github.com/carpedm20/variational-text-tensorflow

Last synced: 3 months ago
JSON representation

TensorFlow implementation of Neural Variational Inference for Text Processing

• Host: GitHub
• URL: https://github.com/carpedm20/variational-text-tensorflow
• Owner: carpedm20
• License: mit
• Created: 2016-03-18T12:12:30.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2016-08-10T10:34:58.000Z (about 8 years ago)
• Last Synced: 2024-07-31T02:16:20.147Z (3 months ago)
• Language: Python
• Size: 2.73 MB
• Stars: 541
• Watchers: 27
• Forks: 78
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-starred - variational-text-tensorflow - TensorFlow implementation of Neural Variational Inference for Text Processing (Python)

README

        
Neural Variational Document Model

=================================

Tensorflow implementation of [Neural Variational Inference for Text Processing](http://arxiv.org/abs/1511.06038).

![model_demo](./assets/model.png)

This implementation contains:

1. Neural Variational Document Model

    - Variational inference framework for generative model of text

    - Combines a stochastic document representation with a bag-of-words generative model 

2. Neural Answer Selection Model (in progress)

    - Variational inference framework for conditional generative model of text

    - Combines a LSTM embeddings with an attention mechanism to extract the semantics between question and answer

Prerequisites

-------------

- Python 2.7 or Python 3.3+

- [NLTK](http://www.nltk.org/)

- [TensorFlow](https://www.tensorflow.org/)

Usage

-----

To train a model with Penn Tree Bank dataset:

    $ python main.py --dataset ptb

To test an existing model:

    $ python main.py --dataset ptb --forward_only True

Results

-------

Training details of NVDM. The best result can be achieved by onehost updates, not alternative updates.

![scalar](./assets/2016-03-20-final-scalar.png)

![histogram](./assets/2016-03-20-final-hist.png)

Author

------

Taehoon Kim / [@carpedm20](http://carpedm20.github.io/)