Closed JepsonWong closed 6 years ago
The meaning of the paper should be two layers of lstm followed by cnn layer features, why is there no lstm and cnn in your code?
When you get context right, you reverse the input sequences, but you don't reverse the output sequences. I think the output seqences should be reversed. By the way, do you implement a rnn cell by yourself in your source code? So you don't use the tensorflow's api. thanks.@brightmart
I guess the author implement a rnn cell in his source code. https://github.com/brightmart/text_classification/blob/a552e115a54b3d3f0736d418bd1b41a30550815b/a04_TextRCNN/p71_TextRCNN_model.py#L51 this is the rnn weights. @fei161
The author first makes a full connection to the context. Then concatenates the context vector concat and maximizes it. Finally connects to the full connection layer. @JepsonWong
yes, i know this. I just think that when we get context right, we should reverse the output sequences. @fei161
this is just like taking context information(from left and right) into considering when encode a position to get rich information.
发件人: JepsonWong notifications@github.com 发送时间: 2018年5月8日 10:35 收件人: brightmart/text_classification 抄送: Subscribed 主题: [brightmart/text_classification] 请问p71_TextRCNN_model.py中rnn-cnn layer定义原理是什么?最后ensemble left, embedding, right to output的方式不像Bi-LSTM layer呀 (#51)
― You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/brightmart/text_classification/issues/51, or mute the threadhttps://github.com/notifications/unsubscribe-auth/ASuYMBBs4EfV-B6kxlCdTJQoiUPb648Nks5twQRVgaJpZM4T17Mv.