Multi-Zone Unit for Recurrent Neural Networks


  • Fandong Meng Tencent
  • Jinchao Zhang Tencent
  • Yang Liu Tsinghua University
  • Jie Zhou Tencent



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.




How to Cite

Meng, F., Zhang, J., Liu, Y., & Zhou, J. (2020). Multi-Zone Unit for Recurrent Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5150-5157.



AAAI Technical Track: Machine Learning