TAF PUBLISHING

Sentence classification of shortened text such as single sentences of movie review is a hard subject because of the limited finite information that they normally contain. We present a Convolutional Neural Network (CNN) architecture and better hyper-parameter values for learning sentence classification with no preprocessing on small sized data. The CNN used in this work have multiple stages. First the input layer consist of sentence concatenated word embedding. Then followed by convolutional layer with different filter sizes for learning sentence level features, followed by max-pooling layer which concatenate features to form final feature vector. Lastly a softmax classifier is used. In our work we allow network to handle arbitrarily batch size with different dropout ratios, which is gave us an excellent way to regularize our CNN and block neurons from co-adapting and impose them to learn useful features. By using CNN with multi filter sizes we can detect specific features such as existence of negations like “not amazing”. Our approach achieves state-of-the-art result for sentence sentiment prediction in both binary positive/negative classification.