Machine translating device based on intelligent matching and method thereof

Abstract

The invention designs a machine translating device based on intelligent matching and a method of the machine translating device. The method comprises the following steps of: A step, carrying out a linguistic data pre-processing step: carrying out word frequency counting and marking on sub-domain linguistic data; B step, carrying out a sentence database establishing step: establishing the sentence database by using sub-domain English-to-Chinese linguistic data; C step, carrying out a word database establishing step: establishing a word database according to the linguistic data pre-processing step and the sentence database establishing step; and D step, carrying out a machine translating step: firstly, manually making a phrase framework consisting of Chinese phrase nodes and a translation rule of the phrase framework according to the sentence database establishing step and the word database establishing step, and identifying a rule of a Chinese sentence sub point; automatically generating a sentence framework template base by using the sentence database, grammar identification and the phrase framework; and finding a framework matching sentence.

Description

technical field [0001] The present invention relates to the technical field of machine translation, in particular to a machine translation device and method based on intelligent matching. Background technique [0002] With the trend of technology and economic globalization, it is increasingly urgent to overcome language barriers to facilitate international exchanges. Specifically, on the one hand, users can directly read and understand non-native language materials; on the other hand, assistant translators can complete written translation more accurately, labor-savingly and efficiently. [0003] High expectations are placed on machine translation technology, which mainly includes two parts: corpus (sentence library / thesaurus) construction and sentence translation. Obviously, manually building a corpus is costly and inefficient. At present, when a machine builds a sentence database, the division of parallel corpus comparison areas is relatively mechanical and cumbersome. a...

AI Technical Summary

Problems solved by technology

However, this patent document (D1) has the following disadvantages: (1) Find the optimal segment combination in the sentence base according to the feature function, and the feature function refers to the various translations contained in the translation generation model of the machine translation system based on bilingual examples Knowledge, such as: similarity between the sentence to be translated and the example sentence, the credibility of the example sentence, the fluency of the translation

However, this patent document (D2) has the following disadvantages: D2 searches for example sentences in the first language that are similar to the sentences to be translated from the constructed general example sentence database, prepares corresponding translations for the part of the first language distinction between the two, and then combines the similar parts of the two Combined with the translation of the difference part to generate a reference translation

The similarities and differences in the first language of the sentence are limited to the level of the meaning of the text itself, and the language characteristics (such as the key elements of the sentence) are relatively ignored, and the accuracy is not enough

Images