Abstract | ||
---|---|---|
Neural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. This makes it more difficult to train the model and poses a risk of information loss to prediction. In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. In particular, we design three fusion functions to learn a better representation from the stack. Experimental results show that our approach yields improvements of 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. The result is new state-of-the-art in German-English translation. |
Year | Venue | Field |
---|---|---|
2018 | COLING | Multi layer,Pattern recognition,Computer science,Machine translation,Fusion,Artificial intelligence |
DocType | Volume | Citations |
Conference | C18-1 | 3 |
PageRank | References | Authors |
0.38 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qiang Wang | 1 | 3 | 0.72 |
Fuxue Li | 2 | 3 | 0.72 |
Tong Xiao | 3 | 131 | 23.91 |
Yanyang Li | 4 | 5 | 2.46 |
Yinqiao Li | 5 | 6 | 2.47 |
Jingbo Zhu | 6 | 703 | 64.21 |