Exploring the Construction of English Translation Corpus and Application of Translation Teaching in Colleges and Universities Based on Parallel Computing

Abstract

The article first collects Chinese-English bilingual corpus through web crawler technology, and then constructs a preliminary Chinese-English bilingual corpus by unifying coding and filtering to improve the quality of the corpus. After that, a distributed system based simple Bayesian algorithm is used to realize large-scale text mining and classification. Then a parallel corpus of English-Chinese translation in colleges and universities is constructed, and a model of the corpus assisting English teaching in colleges and universities is designed, and the practical application effect of the model is analyzed. The results show that: the classification accuracy of this paper's algorithm on the experimental corpus can be stabilized above 95%, and this paper's algorithm works well in the parallel computing performance test, which can straightly keep a lower scale ratio, so that the clusters can be more fully utilized, and has better parallelism. Under the corpus-assisted English teaching practice in colleges and universities, the English proficiency of the students in the experimental class is significantly higher than that of the control class (p<0.05), especially in the “vocabulary and grammatical structure, translation, writing” questions, there is a significant difference in the effect between the control class and the experimental class.