首页|Findings on Machine Translation Reported by Investigators at University of the S ciences (Xlit: a Method To Bridge Task Discrepancy In Machine Translation Pre-tr aining)
Findings on Machine Translation Reported by Investigators at University of the S ciences (Xlit: a Method To Bridge Task Discrepancy In Machine Translation Pre-tr aining)
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 newsoriginating from Ho Chi Minh, Viet nam, by NewsRx correspondents, research stated, “Transfer learningfrom pre-trai ned language models to encoder-decoder translation models faces a challenge due to themismatch between the tasks of pre-training and fine-tuning. Pre-trained m odels are not explicitly trainedto understand the semantic interactions between different languages.”
Ho Chi MinhVietnamAsiaEmerging Tec hnologiesMachine LearningMachine TranslationUniversity of the Sciences
NETL
NSTL
