Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-03 Cooperative journals: 《计算机应用研究》
Abstract: Focused on the issue of semantic independence in Chinese-Uyghur statistical machine translation system, this paper proposed a bilingual relatedness optimization model based on neural machine translation method. The model utilized the attention mechanism to capture word alignment information as well as introduced bilingual phrase semantic relevance and inner word correlation to predict the conditional probability of bilingual phrase pair. And then took the probability as bilingual relatedness to optimize the phrase translation scores in statistical translation model. Experimental results on the 11th China Workshop on Machine Translation (CWMT 2015) Chinese-Uyghur public machine translation datasets show that the proposed approach can achieve obvious improvements both in the phrase-level and the sentence-level machine translation tasks, which outperforms the baseline system with a relative small-scale training data and vocabulary. The highest BLEU point gains are 2.49 and 0.59 respectively.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-02 Cooperative journals: 《计算机应用研究》
Abstract: To design a training model with stable computational performance and high accuracy which is applied on a small training dataset has been a difficult and challenging problem in the field of machine learning. This paper proposed a Resource Allocating Networks with Extended Kalman Filter (RANEKFs) based parallel ensemble learning algorithm. The learning system is composed of multiple RANEKF units, and the unit inputs are produced by the original dataset with random initialized weights. Based on the experiment results conducted on a small dataset, it is found that the novel model outperforms the ensemble learning systems constructed by the other artificial neural networks in terms of the computational accuracy and stability.