Depth-Adaptive Transformer
share
State of the art sequence-to-sequence models 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. Experiments on machine translation benchmarks show that this approach can match the accuracy of a baseline Transformer while using only half the number of decoder layers.
READ FULL TEXT