Machine translation word order adjusting method

Abstract

The invention relates to the field of machine translation, in particular to a machine translation word order adjusting method. Translated word order adjusting rule templates are introduced to machine learning, source texts, standard translated texts and machine translated texts are compared according to the rule templates, translated word order adjusting rules are extracted from a training set, and the positions of current words and replacement words in 'Crossover' word pairs are exchanged according to the rules. According to the method, the order adjusting rules are extracted through template matching to form rule sequences, and the rule sequences are applied to adjust word order errors in the corresponding machine translated texts so as to make the word orders of the machine translated texts more natural and conform to syntactic structures and wording habits of target languages. In addition, the machine translation word order adjusting method can be applied to mutual translation of any two languages, can correct the word order problems of corresponding translation systems in a targeted mode, the automation degree is high, and the labor and time costs for later manual editing are remarkably reduced.

Description

technical field [0001] The invention relates to the field of machine translation, in particular to a method for adjusting word order in machine translation. Background technique [0002] Now that the Internet has spread all over the world, people from different nationalities and nationalities can share and exchange information anytime and anywhere; people are eager to obtain all the information on the Internet quickly and smoothly. Therefore, there is a huge market demand for accurate and efficient automatic machine translation between multiple languages ​​in the current and future international atmosphere. However, an Internet multilingual translation system with high performance, powerful functions and high accuracy still needs to overcome many major technical difficulties under the current technical level. With the current level of machine translation, high-quality usable machine translations are still unavailable. The current general way to solve this problem is to use...

AI Technical Summary

Problems solved by technology

[0004] In addition, among the repeated errors in machine translation, the wrong order of words in the translated text and the wrong word order and grammar are one of the basic mistakes. Word order errors of be verbs / modal verbs (MD) phrases, sentence order errors of neighbor phrases, etc.) account for a large proportion of the total errors in machine translation, and in view of the huge grammatical differences between different languages, word order errors in The probability of occurrence in machine translation is very high, and word order errors greatly affect the degree of specialization of machine translation; at the same time, due to the complexity of word order and grammar itself, it is difficult to correct machine translation word order or grammatical errors in manual post-editing. Large; and compared to translation errors, word order and grammatical errors have a higher repetition rate. If they are all adjusted by manual post-editing, it will consume a lot of manpower and time.

Images