WSEAS Transactions on Information Science and Applications
Print ISSN: 1790-0832, E-ISSN: 2224-3402
Volume 16, 2019
Evaluation of Two Different Models in Neural Machine Translation
Author:
Abstract: This paper introduces two different models in Neural Machine Translation task and evaluates their performances. In the evaluation, the research is based on the Chinese-English news and English-Chinese news machine translation evaluation task. For the translation of the Chinese-English orientation, we used traditional hierarchical phrase model. In the English-Chinese translation direction, we used not only the traditional hierarchical phrase model but also the RNN neural network model and the attention model. At the same time, we compared and analyzed the translation results. In the remainder of this article, we introduce the system framework, data process approach and evaluation results in various evaluation tasks