Transformers without Tears: Improving the Normalization of Self-Attention

Toan Q. Nguyen, Julian Salazar


Abstract
We evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PRENORM) and smaller initializations enable warmup-free, validation-based training with large learning rates. Second, we propose l2 normalization with a single scale parameter (SCALENORM) for faster training and better performance. Finally, we reaffirm the effectiveness of normalizing word embeddings to a fixed length (FIXNORM). On five low-resource translation pairs from TED Talks-based corpora, these changes always converge, giving an average +1.1 BLEU over state-of-the-art bilingual baselines and a new 32.8 BLEU on IWSLT '15 English-Vietnamese. We ob- serve sharper performance curves, more consistent gradient norms, and a linear relationship between activation scaling and decoder depth. Surprisingly, in the high-resource setting (WMT '14 English-German), SCALENORM and FIXNORM remain competitive but PRENORM degrades performance.
Anthology ID:
2019.iwslt-1.17
Volume:
Proceedings of the 16th International Conference on Spoken Language Translation
Month:
November 2-3
Year:
2019
Address:
Hong Kong
Venues:
EMNLP | IWSLT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
Language:
URL:
https://aclanthology.org/2019.iwslt-1.17
DOI:
Bibkey:
Cite (ACL):
Toan Q. Nguyen and Julian Salazar. 2019. Transformers without Tears: Improving the Normalization of Self-Attention. In Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Transformers without Tears: Improving the Normalization of Self-Attention (Nguyen & Salazar, IWSLT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2019.iwslt-1.17.pdf
Code
 tnq177/transformers_without_tears +  additional community code