We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
你好,我想请问下,在span light conv中,既然已经用tf.layers.separable_conv1d生成了带span信息的矩阵key_conv_attn_layer,为什么还需要点乘query_layer呢?对应于conv_attn_layer = tf.multiply(key_conv_attn_layer, query_layer)。感觉此处点乘不是很有必要
The text was updated successfully, but these errors were encountered:
您好,因为self-attention中是, 我们这里使用二者点乘的一个intuition是和self-attention保持一致,即产生的kernel也是input的两个线性变换乘积再经过softmax。 另一方面,我们认为产生的convolution kernel可以部分理解成当前token和附近neighbor tokens的关系,而不仅仅只是带有当前span的信息,所以我们采用了二者的点乘再经过softmax来生成卷积核。
Sorry, something went wrong.
No branches or pull requests
你好,我想请问下,在span light conv中,既然已经用tf.layers.separable_conv1d生成了带span信息的矩阵key_conv_attn_layer,为什么还需要点乘query_layer呢?对应于conv_attn_layer = tf.multiply(key_conv_attn_layer, query_layer)。感觉此处点乘不是很有必要
The text was updated successfully, but these errors were encountered: