In this paper, we propose a multilingual encoder-decoder architecture capable
of obtaining multilingual sentence representations by means of incorporating an
intermediate {\em attention bridge} that is shared across all languages. That
is, we train the model with language-specific encoders and decoders that are
connected via self-attention with a shared layer that we call attention bridge.
This layer exploits the semantics from each language for performing translation
and develops into a language-independent meaning representation that can
efficiently be used for transfer learning. We present a new framework for the
efficient development of multilingual NMT using this model and scheduled
training. We have tested the approach in a systematic way with a multi-parallel
data set. We show that the model achieves substantial improvements over strong
bilingual models and that it also works well for zero-shot translation, which
demonstrates its ability of abstraction and transfer learning.

本文提出了一种多语言编码器 - 解码器架构，其中包括一个中间的共享‘注意桥接层’，能够获取多语言句子代表。我们通过以一种我们称之为‘注意力桥’的共享层连接带有语言特定编码器和解码器的模型来训练，并展示了一种新的框架来高效实现多语言 NMT。在多重平行数据集中系统地测试了该方法，结果表明该模型能显著提高强度双语模型的性能，并且也可以用于零 - shot 翻译，展示了其抽象和转移学习的能力。