Improving Neural Machine Translation by Bidirectional Training

Abstract

We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from "src$\to$tgt" to "src+tgt$\to$tgt+src" without any complicated model modifications. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experimental results show that BiT pushes the SOTA neural machine translation performance across 15 translation tasks on 8 language pairs (data sizes range from 160K to 38M) significantly higher. Encouragingly, our proposed model can complement existing data manipulation strategies, i.e. back translation, data distillation, and data diversification. Extensive analyses show that our approach functions as a novel bilingual code-switcher, obtaining better bilingual alignment.

EMNLP 2021. arXiv admin note: text overlap with arXiv:2107.11572

References in corpus (6)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Multilingual Denoising Pre-training for Neural Machine Translation
• Dual Learning for Machine Translation
• Pay Less Attention with Lightweight and Dynamic Convolutions
• Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
• The USYD-JD Speech Translation System for IWSLT 2021