Victor Li


2020

pdf bib
On the Sparsity of Neural Machine Translation Models
Yong Wang | Longyue Wang | Victor Li | Zhaopeng Tu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of computational resources. In response to this problem, we empirically investigate whether the redundant parameters can be reused to achieve better performance. Experiments and analyses are systematically conducted on different datasets and NMT architectures. We show that: 1) the pruned parameters can be rejuvenated to improve the baseline model by up to +0.8 BLEU points; 2) the rejuvenated parameters are reallocated to enhance the ability of modeling low-level lexical information.