Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

训练的准确率91%,实际测试效果和与作者提供的demo有点差距,请问大神如何能达到和demo一样的效果 #102

Open
midsummer128 opened this issue Dec 2, 2017 · 9 comments

Comments

@midsummer128
Copy link

训练模型准确率91%,实际测试效果和与作者提供的demo有点差距,请问大神如何能达到和demo一样的效果

@midsummer128
Copy link
Author

现在准确率到97.55%,和demo还是有差距。分词效果:
{
"pos": "gb",
"tok": "长江形成"
},
{
"pos": "t",
"tok": "今年"
},
{
"pos": "nz",
"tok": "第一号"
},
{
"pos": "n",
"tok": "洪水"
}
请问大神如何能做到demo的效果

@qujinqiang
Copy link

@midsummer128 你有基于原始结构进行调整吗? 我windows的,不知道该怎么跑。。。

@midsummer128
Copy link
Author

@qujinqiang 没有调整原始结构,我是在linux跑的,虚拟机

@qujinqiang
Copy link

qujinqiang commented Jan 24, 2018

@midsummer128 我也是用2014的语料做的训练,准确率也就91%;
整体结构跟kcws 类似 也是采用bi-lstm + crf
请问兄是怎么跑到97%的?
兄要是方便交流的话还望加下我的Q:273459197

@nwy2010
Copy link

nwy2010 commented Apr 23, 2018

我跑了下也是91%,demo的97%怎么跑的?

@AlleyEli
Copy link

用2014+1998的语料库,IDCNN可以跑到98.35%左右

@midsummer128
Copy link
Author

@AlleyEli 感谢回复,是否有命名实体识别的训练方法,基于BiLSTM-CRF模型的命名实体识别的语料标注方法

@qujinqiang
Copy link

@midsummer128 这个确实蛋疼,有好的方法还望交流

@AlleyEli
Copy link

AlleyEli commented Jul 6, 2018

@midsummer128 命名实体识别没有单独搞, 不过IDCNN和BILSTM都命名实体识别都不太理想

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants