Log In Sign Up

Accelerating Neural Transformer via an Average Attention Network

by   Biao Zhang, et al.

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer. The average attention network consists of two layers, with an average layer that models dependencies on previous positions and a gating layer that is stacked over the average layer to enhance the expressiveness of the proposed attention network. We apply this network on the decoder part of the neural Transformer to replace the original target-side self-attention model. With masking tricks and dynamic programming, our model enables the neural Transformer to decode sentences over four times faster than its original version with almost no loss in training time and translation performance. We conduct a series of experiments on WMT17 translation tasks, where on 6 different language pairs, we obtain robust and consistent speed-ups in decoding.


page 1

page 2

page 3

page 4


Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence

Object Detection with Transformers (DETR) and related works reach or eve...

Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network

Due to the highly parallelizable architecture, Transformer is faster to ...

An Efficient Transformer Decoder with Compressed Sub-layers

The large attention-based encoder-decoder network (Transformer) has beco...

Mask Attention Networks: Rethinking and Strengthen Transformer

Transformer is an attention-based neural network, which consists of two ...

Sharing Attention Weights for Fast Transformer

Recently, the Transformer machine translation system has shown strong re...

Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering

We consider the design of two-pass voice trigger detection systems. We f...

Type Anywhere You Want: An Introduction to Invisible Mobile Keyboard

Contemporary soft keyboards possess limitations: the lack of physical fe...