$gen$CNN: A Convolutional Architecture for Word Sequence Prediction
This work addresses language modeling and generation for NLP applications, offering a fast and parallelizable alternative to RNNs and LSTMs.
The authors tackled word sequence prediction by proposing a convolutional architecture, $gen$CNN, which outperformed state-of-the-art methods in text generation and machine translation re-ranking with significant margins.
We propose a novel convolutional architecture, named $gen$CNN, for word sequence prediction. Different from previous work on neural network-based language modeling and generation (e.g., RNN or LSTM), we choose not to greedily summarize the history of words as a fixed length vector. Instead, we use a convolutional neural network to predict the next word with the history of words of variable length. Also different from the existing feedforward networks for language modeling, our model can effectively fuse the local correlation and global correlation in the word sequence, with a convolution-gating strategy specifically designed for the task. We argue that our model can give adequate representation of the history, and therefore can naturally exploit both the short and long range dependencies. Our model is fast, easy to train, and readily parallelized. Our extensive experiments on text generation and $n$-best re-ranking in machine translation show that $gen$CNN outperforms the state-of-the-arts with big margins.