logicxin / SummaRuNNer-1

Tensorflow implementation of SummaRuNNer

Home Page:https://arxiv.org/pdf/1611.04230.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

SummaRuNNer(实现基本没问题)

Tensorflow implementation of SummaRuNNer

the version of Tensorflow is 1.2.0

Usage: Now data & w2v model is provided, you can use them to train a model directly, then you should change the model directory to your trained model position for evaluation.

Data & w2v model: 链接: https://pan.baidu.com/s/1AVwjhBTkkbpUMgo7DAg73w 提取码: ywf5
Google: https://drive.google.com/drive/folders/1Ym2BcE2MBkxfPYWOfzwbrhpJo51OgFlJ?usp=sharing

Reference: hpzhao 's PyTorch implementation of SummaRuNNer https://github.com/hpzhao/SummaRuNNer

Result: in our data, it gets almost the same result with the Pytorch one. for ndcg@5, the difference between them is no more than 0.004(~0.5%).

If you have any questions, please feel free to contact me.

About

Tensorflow implementation of SummaRuNNer

https://arxiv.org/pdf/1611.04230.pdf

License:MIT License


Languages

Language:Python 100.0%