Convolutional Sequence Modeling Revisited

ICLR 2018 Shaojie BaiJ. Zico KolterVladlen Koltun

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... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Language Modelling WikiText-103 Temporal CNN Validation perplexity - # 18
Test perplexity 45.2 # 32