首页|Findings in the Area of Machine Translation Reported from Westlake University (O n Compositional Generalization of Transformerbased Neural Machine Translation)
Findings in the Area of Machine Translation Reported from Westlake University (O n Compositional Generalization of Transformerbased 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-Researchers detail new data in Machine Translation. According to news reporting originatingin Zhejiang, People's Repu blic of China, by NewsRx journalists, research stated, "Neural networkshave bee n shown to have deficiencies in the ability of compositional generalization whil e existing workhas generally targeted semantic parsing tasks. In this paper, we study the challenge of machine translationand introduce a dedicated Chinese -> English dataset, CoGniTion ( Co mpositional G eneralizatio n Machi ne T ransla t ion ). The training, validation, and test sets have 216k, 10k, and 10k sentenc e pairs,respectively, which are simple but contain a variety of phrases."Financial supporters for this research include Ministry of Science and Technolog y, China, ZhejiangProvince Key Project.
ZhejiangPeople's Republic of ChinaAs iaEmerging TechnologiesMachine LearningMachine TranslationWestlake Unive rsity
NETL
NSTL
