Convolutional Neural Networks for Sentence Classification
- A simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks.
- Convolution applied over words - different kernels/filters for different ngrams.
- Apply pooling over time.
- Use dropout.
- A model with two sets of word vectors. Each set of vectors is treated as a ‘channel’ and each filter is applied to both channels, but gradients are backpropagated only through one of the channels.
- Hence the model is able to fine-tune one set of vectors while keeping the other static. Both channels are initialized with word2vec.
Code. Learn. Explore