Recurrent neural networks (RNNs) have been widely used to deal with sequence learning problems. The input-dependent transition function, which folds new observations into hidden states to sequentially construct fixed-length representations of arbitrary-length sequences, plays a critical role in RNNs. Based on single space composition, transition functions in existing RNNs often have difficulty in capturing complicated long-range dependencies. In this paper, we introduce a new Multi-zone Unit (MZU) for RNNs. The key idea is to design a transition function that is capable of modeling multiple space composition. The MZU consists of three components: zone generation, zone composition, and zone aggregation. Experimental results on multiple datasets of the character-level language modeling task and the aspect-based sentiment analysis task demonstrate the superiority of the MZU.
@article{arxiv.1911.07184,
title = {Multi-Zone Unit for Recurrent Neural Networks},
author = {Fandong Meng and Jinchao Zhang and Yang Liu and Jie Zhou},
journal= {arXiv preprint arXiv:1911.07184},
year = {2019}
}