Do Transformer Modifications Transfer Across Implementations and Applications?
Abstract
The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption. In this paper, we comprehensively evaluate many of these modifications in a shared experimental setting that covers most of the common uses of the Transformer in natural language processing. Surprisingly, we find that most modifications do not meaningfully improve performance. Furthermore, most of the Transformer variants we found beneficial were either developed in the same codebase that we used or are relatively minor changes. We conjecture that performance improvements may strongly depend on implementation details and correspondingly make some recommendations for improving the generality of experimental results.
Cite
@article{arxiv.2102.11972,
title = {Do Transformer Modifications Transfer Across Implementations and Applications?},
author = {Sharan Narang and Hyung Won Chung and Yi Tay and William Fedus and Thibault Fevry and Michael Matena and Karishma Malkan and Noah Fiedel and Noam Shazeer and Zhenzhong Lan and Yanqi Zhou and Wei Li and Nan Ding and Jake Marcus and Adam Roberts and Colin Raffel},
journal= {arXiv preprint arXiv:2102.11972},
year = {2021}
}
Comments
To appear at EMNLP 2021 as a conference paper