首页|Researchers from Shanghai Jiao Tong University Report New Studies and Findings I n the Area of Machine Translation (Motransformer: Extract High-level Relationsh ip Between Words for Neural Machine Translation)
Researchers from Shanghai Jiao Tong University Report New Studies and Findings I n the Area of Machine Translation (Motransformer: Extract High-level Relationsh ip Between Words for Neural Machine Translation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Current study results on Machine Trans lation have been published. According to newsreporting originating from Shangha i, People’s Republic of China, by NewsRx correspondents, researchstated, “In th is paper, we propose an explanation of representation for self-attention network (SAN)based neural sequence encoders, which regards the information captured by the model and the encodingof the model as graph structure and the generation o f these graph structures respectively. The proposedexplanation applies to exist ing works on SAN-based models and can explain the relationship among theability to capture the structural or linguistic information, depth of model, and length of sentence, and canalso be extended to other models such as recurrent neural network based models.”
ShanghaiPeople’s Republic of ChinaAs iaEmerging TechnologiesMachine LearningMachine TranslationShanghai Jiao Tong University
NETL
NSTL
