With the development of feed-forward models, the default model for sequence modeling has gradually evolved to replace recurrent networks. Many powerful feed-forward models based on convolutional networks and attention mechanisms were proposed and show more potential to handle sequence modeling tasks. We wonder that is there an architecture that can not only achieve an approximate substitution of recurrent networks but also absorb the advantages of feed-forward models. So we propose an exploratory architecture referred to Temporal Convolutional Attention-based Network (TCAN) which combines temporal convolutional network and attention mechanism. TCAN includes two parts, one is Temporal Attention (TA) which captures relevant features inside the sequence, the other is Enhanced Residual (ER) which extracts the shallow layer's important information and transfers to deep layers. We improve the state-of-theart results of bpc/perplexity to 26.92 on word-level PTB, 1.043 on character-level PTB, and 6.66 on WikiText-2.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.