基于CNN词根形态选择模型的改进蒙汉机器翻译研究

随着科学技术的发展,以循环神经网络为基础的机器翻译方法由于翻译质量更好而逐渐取代统计机器翻译方法,特别是在国际大语种之间的互译方面,RNN在对语料编码时能够提取更好的特征,这对翻译质量好坏至关重要。然而在蒙古语这类小语种的翻译方面,由于语料不足导致的数据稀疏和RNN模型训练梯度消失等问题,很难从语料中充分获取语义关系,因此该文提出一种基于卷积神经网络CNN(convolutional neural network)的蒙汉机器翻译方法,在对源语料编码时利用池化层获取语义关系,并根据蒙古语构词特点得到句子的语义信息,再通过融合全局注意力机制的GRU循环神经网络将编码过后的源语言解码为汉语。实验结果表明,该方法在翻译准确率和训练速度两方面均优于RNN基准机器翻译方法。

Mongolian-Chinese Machine Translation Based on CNN Etyma Morphological Selection Model

The machine translation based on recurrent neural network is gradually replacing the statistical machine translation, especially between the major languages in the world. I Due to the shortage of Mongolian corpus, a method of Mongolian-Chinese machine translation based on Convolutional Neural Network is proposed. In the process of encoding the source corpus, through the pooling layer, the semantic relation and information of CNN in the sentence can be obtained according to the characteristics of Mongolian word formation. The experimental result shows that the method outperforms RNN NMT in the aspect of the quality and training speed of the translation.