Dynamic Multi-Branch Layers for On-Device Neural Machine Translation

• Published in: IEEE/ACM transactions on audio, speech, and language processing speech, and language processing, 2022, Vol.30, p.958-967
• Main Authors: Tan, Zhixing, Yang, Zeyuan, Zhang, Meng, Liu, Qun, Sun, Maosong, Liu, Yang
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Conditional computation; decoding; Electronic devices; Hardware; Machine translation; Mobile handsets; natural language processing; Performance enhancement; Performance evaluation; Training; Transformers; Translations
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2022.3153257

With the rapid development of artificial intelligence (AI), there is a trend in moving AI applications, such as neural machine translation (NMT), from cloud to mobile devices. Constrained by limited hardware resources and battery, the performance of on-device NMT systems is far from satisfactory. Inspired by conditional computation, we propose to improve the performance of on-device NMT systems with dynamic multi-branch layers. Specifically, we design a layer-wise dynamic multi-branch network with only one branch activated during training and inference. As not all branches are activated during training, we propose shared-private reparameterization to ensure sufficient training for each branch. At almost the same computational cost, our method achieves improvements of up to 1.7 BLEU points on the WMT14 English-German translation task and 1.8 BLEU points on the WMT20 Chinese-English translation task over the Transformer model, respectively. Compared with a strong baseline that also uses multiple branches, the proposed method is up to 1.5 times faster with the same number of parameters.