Keywords: Temporal Convolutional Network, Sequence Modeling, Deep Learning
TL;DR: We argue that convolutional networks should be considered the default starting point for sequence modeling tasks.
Abstract: This paper revisits the problem of sequence modeling using convolutional architectures. Although both convolutional and recurrent architectures have a long history in sequence prediction, the current "default" mindset in much of the deep learning community is that generic sequence modeling is best handled using recurrent networks. The goal of this paper is to question this assumption. Specifically, we consider a simple generic temporal convolution network (TCN), which adopts features from modern ConvNet architectures such as a dilations and residual connections. We show that on a variety of sequence modeling tasks, including many frequently used as benchmarks for evaluating recurrent networks, the TCN outperforms baseline RNN methods (LSTMs, GRUs, and vanilla RNNs) and sometimes even highly specialized approaches. We further show that the potential "infinite memory" advantage that RNNs have over TCNs is largely absent in practice: TCNs indeed exhibit longer effective history sizes than their recurrent counterparts. As a whole, we argue that it may be time to (re)consider ConvNets as the default "go to" architecture for sequence modeling.
Data: [LAMBADA](https://paperswithcode.com/dataset/lambada), [MNIST](https://paperswithcode.com/dataset/mnist), [Penn Treebank](https://paperswithcode.com/dataset/penn-treebank), [WikiText-103](https://paperswithcode.com/dataset/wikitext-103), [WikiText-2](https://paperswithcode.com/dataset/wikitext-2)