Train convolutional network for sentiment analysis. Based on "Convolutional Neural Networks for Sentence Classification" by Yoon Kim, link. Inspired by Denny Britz article "Implementing a CNN for Text Classification in TensorFlow", link. "CNN-rand" and "CNN-non-static" models get to 88-90%
- larger IMDB corpus, longer sentences; sentence length is very important, just like data size
- smaller embedding dimension, 20 instead of 300
- 2 filter sizes instead of original 3
- much fewer filters; experiments show that 3-10 is enough; original work uses 100
- random initialization is no worse than word2vec init on IMDB corpus
- sliding Max Pooling instead of original Global Pooling