Depth-Adaptive Transformer

Maha Elbayad, Jiatao Gu, Edouard Grave, Michael Auli

Keywords: Deep learning, natural language processing, sequence modeling

TL;DR: Sequence model that dynamically adjusts the amount of computation for each input.

Abstract: State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process. In this paper, we train Transformer models which can make output predictions at different stages of the network and we investigate different ways to predict how much computation is required for a particular sequence. Unlike dynamic computation in Universal Transformers, which applies the same set of layers iteratively, we apply different layers at every step to adjust both the amount of computation as well as the model capacity. On IWSLT German-English translation our approach matches the accuracy of a well tuned baseline Transformer while using less than a quarter of the decoder layers.