一种考虑强调的英语口语翻译模型

An oral english translation model considering emphasis

为了打破跨语言交际中的语言障碍,采用翻译系统实现该目的。传统翻译系统不能很容易地处理单词和强调级别之间关系。此外,由于所有组件都是单独训练的,没有进行联合优化。为此,提出一种基于序列到序列模型的处理连续强调级别的方法,并将机器翻译和强调翻译结合到一个单一的模型中,这大大简化了翻译过程,更容易进行联合优化。实验表明,提出的模型与现有方法相比,具有更好的性能,并且能够较好地满足实际需求。

In order to break the language barriers in cross-language communication,a translation system is used to achieve this goal.Traditional translation systems cannot easily handle the relationship between words and emphasis levels.In addition,since all components are trained separately with no joint optimization.To the erd,a method based on sequence-to-sequence model for processing continuous emphasis levels is proposed here,and machine translation and emphasis translation are combined into a single model,which greatly simplifies the translation process,it is easier to perform joint optimization.Experiments show that the proposed model has better performance than existing methods and can meet actual needs.