问题描述
我正在尝试对电影评论的情绪进行分类，并根据评论本身来预测电影的类型.现在，情感是一个二进制分类问题，因为流派可能是多标签分类问题.
I am trying to classify sentiment on movie review and predict the genres of that movie based on the review itself. Now Sentiment is a Binary Classification problem where as Genres can be Multi-Label Classification problem.
另一个澄清问题的例子是对句子的情感进行分类，并预测句子的语调是快乐，讽刺，悲伤，可怜，生气还是恐惧.
Another example to clarify the problem is classifying Sentiment of a sentence and also predicting whether the tone of the sentence is happy, sarcastic, sad, pitiful, angry or fearful.
更重要的是，我想使用Tensorflow CNN进行此分类.我的问题是构造y_label并训练数据，以使输出帮助我检索情绪和体裁.例如，数据Y标签:[[0,1]，[0,1,0,1,0]]用于表示情绪为负面，情绪为讽刺和愤怒
More to that is, I want to perform this classification using Tensorflow CNN. My problem is in structuring the y_label and training the data such that the output helps me retrieve Sentiment as well as the genres.Eg Data Y Label: [[0,1],[0,1,0,1,0]] for sentiment as Negative and mood as sarcastic and angry
您如何建议我解决这个问题?
How do you suggest I tackle this?
推荐答案
基本上，在将CNN输出的大小调整为1x1xN形式的CNN的最后一层时，添加两个前馈神经网络.因此，如果您有一个简单的分类问题，可以将CNN的输出馈入前馈神经网络，现在在这种情况下，您将拥有其中两个网络.因此，为了基本完成此操作，您将具有以下内容:
Basically at the final layer of the CNN as you've resized the CNN output to a form of 1x1xN, add two Feed-Forward Neural Networks. So if you have a simple classification problem you feed the output of the CNN into a Feed-Forward Neural Network, now in this case you'll have two of these networks. So in order to accomplish this basically you'll have the following:
- CNN输出--- feed --->分类器#1
- CNN输出--- feed --->分类器#2
因此，您必须将分类分开，但仍然需要反向传播它们，因此看起来像这样:
Thus you'll have to separate classifications BUT you'll still have to backpropagate them so it will look something like this:
loss1 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction1, labels_1))
loss2 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction2, labels_2))
loss = loss1 + loss2
因此，您将使用优化器最小化" loss.
So you'll "minimize" the loss with an optimizer.
这篇关于如何使用CNN Tensorflow从电影评论中对情感和流派进行分类的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！