We propose a novel extension of the encoder-decoder framework, called a review network. The review network is generic and can enhance any existing encoder- decoder model: in this paper, we consider RNN decoders with both CNN and RNN encoders. The review network performs a number of review steps with attention mechanism on the encoder hidden states, and outputs a thought vector after each review step; the thought vectors are used as the input of the attention mechanism in the decoder. We show that conventional encoder-decoders are a special case of our framework. Empirically, we show that our framework improves over state-of- the-art encoder-decoder systems on the tasks of image captioning and source code captioning.
@article{arxiv.1605.07912,
title = {Review Networks for Caption Generation},
author = {Zhilin Yang and Ye Yuan and Yuexin Wu and Ruslan Salakhutdinov and William W. Cohen},
journal= {arXiv preprint arXiv:1605.07912},
year = {2016}
}