A Comparative Study Of Man-Machine Translation Of Chinese And Uyghur Words

In recent years,with the continuous development of computer technology,machine translation has been increasingly used in Chinese-Uyghur translation,and its important role in the translation world has become increasingly prominent.This paper is based on the publicly issued "Xi Jinping Governing the Country"(Volume 1 and Volume 2),the original text,the Uyghur version of the manual translation,and the online translation of the machine translation.There are three texts,using Ant Conc3.5.8(windows),Em Editor and other software Tools,establish a trilingual parallel corpus and obtain corpus data.By analyzing the corpus data of the two Uyghur translations of man-machine,a comparative study of word-based man-machine translation is carried out.On the one hand,it examines the human-machine translation of Chinese-Uyghur parts of speech.Chinese-Uyghur machine translation provides suggestions for improvement,with a view to a more comprehensive development of Chinese-Uyghur machine translation in the future.The full text is divided into six parts.The introduction introduces the topic selection and summarizes the existing research results of machine translation.The first chapter is the development and data analysis of the corpus,including class symbols/type symbols,part-of-speech distribution,word frequency and average sentence length,so as to summarize the vocabulary characteristics of the translated text.The second chapter selects the 8 parts of speech with the largest proportion from content words and function words,and discusses the translation of human-machine translations through data analysis and examples.The third chapter is based on the previous data as a support to find that the differences between human-machine translation in word translation are mainly reflected in three aspects: word choice,word form and part of speech category.Chapter 4 discusses the problems of machine translation,and concludes that machine translation has five types of errors: over translation,under translation,word order error,word selection error,and word inflection error.Based on the problems reflected in this article,it is the future machine.The translation provides several optimization suggestions.The conclusion part summarizes the full text.