READING NOTES 2 2018-08-20

1.Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

G:\paper\1412.1058

seq-CNN：a straightforward adaptation of CNN from image to text

image.png

bow-CNN：a simple but new variation of CNN that employs bag-of-word conversion in the convolution layer

image.png

Experimental framework：
activation function ： max(x, 0)
minimized square loss with L2 regularization by stochastic gradient descent (SGD)
network architectures ：one pair of convolution and pooling layers
Out-of-vocabulary words were represented by a zero vector
On bow-CNN：used variable region stride to speed up computation

Data Set：
IMDB: movie reviews
Elec: electronics product reviews
RCV1: topic categorization

Result：

image.png
image.png
image.png