Sharing Attention Weights for Fast Transformer
June 26, 2019 ยท Declared Dead ยท ๐ International Joint Conference on Artificial Intelligence
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Tong Xiao, Yinqiao Li, Jingbo Zhu, Zhengtao Yu, Tongran Liu
arXiv ID
1906.11024
Category
cs.CL: Computation & Language
Citations
59
Venue
International Joint Conference on Artificial Intelligence
Last Checked
3 months ago
Abstract
Recently, the Transformer machine translation system has shown strong results by stacking attention layers on both the source and target-language sides. But the inference of this model is slow due to the heavy use of dot-product attention in auto-regressive decoding. In this paper we speed up Transformer via a fast and lightweight attention model. More specifically, we share attention weights in adjacent layers and enable the efficient re-use of hidden states in a vertical manner. Moreover, the sharing policy can be jointly learned with the MT model. We test our approach on ten WMT and NIST OpenMT tasks. Experimental results show that it yields an average of 1.3X speed-up (with almost no decrease in BLEU) on top of a state-of-the-art implementation that has already adopted a cache for fast inference. Also, our approach obtains a 1.8X speed-up when it works with the \textsc{Aan} model. This is even 16 times faster than the baseline with no use of the attention cache.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computation & Language
๐
๐
Old Age
๐
๐
Old Age
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
RoBERTa: A Robustly Optimized BERT Pretraining Approach
R.I.P.
๐ป
Ghosted
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
R.I.P.
๐ป
Ghosted
Deep contextualized word representations
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
๐ป
Ghosted