摘要
该文探讨了基于RNN和CNN的蒙汉神经机器翻译模型,分别采用蒙古语的词模型、切分模型和子词模型作为翻译系统的输入信号,并与传统的基于短语的SMT进行了比较分析。实验结果表明,子词模型可以有效地提高RNN NMT和CNN NMT的翻译质量。同时实验结果也表明,基于RNN的蒙汉NMT模型的翻译性能已经超过传统的基于短语的蒙汉SMT模型。
In this paper,Mongolian-Chinese neural machine translation model based on RNN and CNN is discussed.Mongolian word model,segmentation model and subword model are used as input signals of the translation system.We compare our method with the traditional phrase-based SMT.Experimental results show that the subword model can effectively improve the quality of NMT and the RNN-based Mongolian-Chinese NMT model has surpassed the traditional phrase-based SMT model.
作者
包乌格德勒
赵小兵
BAO Wugedele;ZHAO Xiaobing(School of Computer,Hohhot Minzu College,Hohhot,Inner Mongolia 010051,China;School of Information Engineering Minzu University of China,Beijing 100081,China)
出处
《中文信息学报》
CSCD
北大核心
2018年第8期60-67,共8页
Journal of Chinese Information Processing
基金
国家语委科研项目(YB125-89)