Input combination strategies for multi-source transformer decoder
arXiv preprint arXiv:1811.04716, 2018•arxiv.org
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
multimodal translation and translation with multiple source languages. The experiments …
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
multimodal translation and translation with multiple source languages. The experiments …
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 multimodal translation and translation with multiple source languages. The experiments show that the models are able to use multiple sources and improve over single source baselines.
arxiv.org