switch-GLAT: Multilingual Parallel Machine Translation Via Code-Switch Decoder

Zhenqiao Song · Hao Zhou · Lihua Qian · Jingjing Xu · Shanbo Cheng · Mingxuan Wang · Lei Li

[ Abstract ]
[ Visit Poster at Spot B3 in Virtual World ] [ OpenReview
Mon 25 Apr 2:30 a.m. PDT — 4:30 a.m. PDT


Multilingual machine translation aims to develop a single model for multiple language directions. However, existing multilingual models based on Transformer are limited in terms of both translation performance and inference speed. In this paper, we propose switch-GLAT, a non-autoregressive multilingual machine translation model with a code-switch decoder. It can generate contextual code-switched translations for a given source sentence, and perform code-switch back-translation, greatly boosting multilingual translation performance. In addition, its inference is highly efficient thanks to its parallel decoder. Experiments show that our proposed switch-GLAT outperform the multilingual Transformer with as much as 1.16 BLEU improvement and 6.6x faster decoding speed in inference.

Chat is not available.