Abstract
English has become one of the most widely used languages in the world. If there is no good translation mechanism for such a widely used language, it will bring trouble to both study and life. At present, the world’s major platforms are committed to the study of English translation strategies. There are translation platforms from different regions and different translation mechanisms. These translation data from different translation platforms have the characteristics of large-scale, multisource, heterogeneity, high dimensions, and poor quality. However, such inconsistent translation data will increase the translation difficulty and translation time. Therefore, it is necessary to improve the quality of translation data to achieve a better translation effect. How to provide a large-scale and efficient translation strategy needs to integrate the translation strategies of various platforms to perform heterogeneous translation data cleaning and fusion based on machine learning. At first, this paper represents the multisource, heterogeneous translation data model as tree-augmented naive Bayes networks (TANs) and naturally captures the relationship between the datasets through the learning of TANs structure and the probability distribution of input attributes and tuples, using data probability value to complete the classification of translation data cleaning. Then, a multisource, heterogeneous translation data fusion model based on recurrent neural network (RNN) is constructed, and RNN is used to control the node data of hidden layer to enhance the fault-tolerant ability in the fusion process and complete the construction of fusion model. Finally, experimental results show that TANs-based translation data cleaning method can effectively improve the cleaning rate with an average improvement of approximately 10% and cleaning time with an average reduce about 5%. In addition, RNN-based multisource translation data fusion method improves the shortcomings of the traditional fusion model and improves the practicability of the fusion model in terms of root mean square error (RMSE), mean absolute percentage error (MAPE), fusion time, and integrity.
Highlights
English has become one of the most widely used languages in the world
This paper represents the multisource, heterogeneous translation data model as tree-augmented naive Bayes networks (TANs) and naturally captures the relationship between the datasets through the learning of TANs structure and the probability distribution of input attributes and tuples, using data probability value to complete the classification of translation data cleaning. en, a multisource, heterogeneous translation data fusion model based on recurrent neural network (RNN) is constructed, and RNN is used to control the node data of hidden layer to enhance the fault-tolerant ability in the fusion process and complete the construction of fusion model
Root mean square error (RMSE), mean absolute percentage error (MAPE), fusion time, and integrity were used for comparison of heterogeneous translation data fusion
Summary
In the process of data acquisition, based on the comprehensiveness of data collection and the integrity of relevant data, data collection usually involves multiple data sources, including a variety of databases, file systems and service interfaces, resulting in complex data types and large data scale. erefore, it is necessary for data cleaning after data acquisition. 3. TANs-Based Translation Data Cleaning e main method to classify multisource, heterogeneous data is to establish and examine the multisource, heterogeneous data network model formed by data relationship. E basic idea of translation data cleaning based on TANs is as follows: according to different eigenvectors of translation data, the translation data attributes to be cleaned are divided into different classes to form multiple Bayesian network structures. Tn under the constraint of class variable C, and δti is the value of the attribute parent (ti) of ti in the maximum weight span tree. According to the principle that TANs does not generate a loop, edges are selected in descending order of edge weight until n − 1 edges are selected, and a completely undirected graph with mutual-information value as weight is constructed. Erefore, TANs-based translation data cleaning steps are as follows. (6) e TANs nodes are sorted and output in descending order according to the score R
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
