Multilingual training of neural machine translation (NMT) systems has led to
impressive accuracy improvements on low-resource languages. However, there are
still significant challenges in efficiently learning word representations in
the face of paucity of data. In this paper, we propose Soft Decoupled Encoding
(SDE), a multilingual lexicon encoding framework specifically designed to share
lexical-level information intelligently without requiring heuristic
preprocessing such as pre-segmenting the data. SDE represents a word by its
spelling through a character encoding, and its semantic meaning through a
latent embedding space shared by all languages. Experiments on a standard
dataset of four low-resource languages show consistent improvements over strong
multilingual NMT baselines, with gains of up to 2 BLEU on one of the tested
languages, achieving the new state-of-the-art on all four language pairs.

本研究提出了一种名为 SDE 的多语言词典编码框架，通过字符编码和语义嵌入空间的共享来实现智能共享词汇级别信息，从而实现在低资源语言中神经机器翻译系统的多语言训练。在标准数据集上的实验表明，与强大的多语言神经机器翻译基线相比，本方法在四种低资源语言中表现出一贯的提高，并在其中一种测试语言上获得了 2 BLEU 的增益，并在所有四种语言对中实现了新的最优状态。