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.

Sign up for GitHub

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

Jump to bottom

关于nil_var #26

Open

shuaihuaiyi opened this issue May 16, 2018 · 1 comment

Contributor

shuaihuaiyi commented May 16, 2018

NER-LSTM-CRF/model.py

Line 210 in 50057fe

self.nil_vars.add(self.feature_weight_dict[feature_name].name)

这个变量似乎是用来在训练时防止embedding矩阵的某些无用的行得到更新，但是这里的缩进导致没有提供预训练词向量的特征对应的embedding不能应用这一机制，是不是有bug呢？

另外，预处理时将前两行都空了出来，似乎是将第0行作为填充，第1行作为未登录词，那么在训练时是否应该将这两行的梯度都替换为0呢？我对于TensorFlow API还很不熟悉，看样子函数zero_nil_slot好像只是替换了一行

Contributor Author

shuaihuaiyi commented May 16, 2018

另外可以问一下您nil是什么意思吗？小弟刚刚入门，这些东西完全不懂

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment