https://github.com/carpedm20/neural-summary-tensorflow

In progress
https://github.com/carpedm20/neural-summary-tensorflow

Last synced: 9 days ago
JSON representation

In progress

• Host: GitHub
• URL: https://github.com/carpedm20/neural-summary-tensorflow
• Owner: carpedm20
• Created: 2016-02-03T17:03:02.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-04-12T02:10:59.000Z (over 7 years ago)
• Last Synced: 2024-07-31T21:56:08.750Z (3 months ago)
• Language: Python
• Homepage:
• Size: 347 KB
• Stars: 273
• Watchers: 32
• Forks: 67
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Attention-Based Summarization

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

Tensorflow implementation of [A Neural Attention Model for Abstractive Summarization](http://arxiv.org/abs/1509.00685). The original code of author can be found [here](https://github.com/facebook/NAMAS).

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

Prerequisites

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

- Python 2.7 or Python 3.3+

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

- [Gensim](https://radimrehurek.com/gensim/)

Usage

-----

To train a model with `duc2013` dataset:

    $ python main.py --dataset duc2013

To test an existing model:

    $ python main.py --dataset duc2014 --forward_only True

(This is still in progress and currently have no access to summarization dataset)

References

----------

- [EMNLP 2015 slide](http://people.seas.harvard.edu/~srush/emnlp2015_slides.pdf)

Author

------

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