R-Transformer: Recurrent Neural Network Enhanced Transformer

Abstract

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation procedure. Therefore, many non-recurrent sequence models that are built on convolution and attention operations have been proposed recently. Notably, models with multi-head attention such as Transformer have demonstrated extreme effectiveness in capturing long-term dependencies in a variety of sequence modeling tasks. Despite their success, however, these models lack necessary components to model local structures in sequences and heavily rely on position embeddings that have limited effects and require a considerable amount of design efforts. In this paper, we propose the R-Transformer which enjoys the advantages of both RNNs and the multi-head attention mechanism while avoids their respective drawbacks. The proposed model can effectively capture both local structures and global long-term dependencies in sequences without any use of position embeddings. We evaluate R-Transformer through extensive experiments with data from a wide range of domains and the empirical results show that R-Transformer outperforms the state-of-the-art methods by a large margin in most of the tasks. We have made the code publicly available at \url{https://github.com/DSE-MSU/R-transformer}.

References in corpus (7)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• On the difficulty of training Recurrent Neural Networks
• WaveNet: A Generative Model for Raw Audio
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Full-Capacity Unitary Recurrent Neural Networks

Cited by in corpus (5)

• ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context
• Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
• Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention
• I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths
• Depth-Adaptive Graph Recurrent Network for Text Classification