Multilingual Neural Machine Translation With Soft Decoupled Encoding

Xinyi Wang, Hieu Pham, Philip Arthur, Graham Neubig

Abstract: 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.

Code: [ cindyxinyiwang/SDE](https://github.com/cindyxinyiwang/SDE)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1902.03499/code)