In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the encoder-decoder attention in the Transformer architecture. We propose four different input combination strategies for the encoder-decoder attention: serial, parallel, flat, and hierarchical. We evaluate our methods on tasks of multi-modal translation and translation with multiple source languages. The experiments show that the models are able to use multiple sources and improve over single source base-lines.
Additional resources: https://arxiv.org/abs/1811.04716