We can use CNN to classify more than 10 thousands of images of the ImageNet.
I find that CNN could only classify 10-20 text classes as this paper write.
So what is the high limit of short text classification's classes' number?
That's interesting. Since CNN can be used to classify images into thousands of labels, I would also expect it able to classify thousands of labels when used for text classification...
We can use CNN to classify more than 10 thousands of images of the ImageNet. I find that CNN could only classify 10-20 text classes as this paper write. So what is the high limit of short text classification's classes' number?