Method and system for determining intertranslation relationship of bilingual sentence pairs

Abstract

The invention discloses a method and system for determining an intertranslation relationship of bilingual sentence pairs. The method comprises a step of determining matching feature values of the bilingual sentence pairs, performing filtering and classification on the bilingual sentence pairs according to the weights of the matching feature values in the intertranslation relationship according to a pre-established training classification model, and determining whether the bilingual sentence pairs are bilingual sentence pairs satisfying the requirements of the intertranslation relationship. Therefore, by adoption of the method for determining the intertranslation relationship of the bilingual sentence pairs provided by the embodiment of the invention, a bilingual corpus with a huge data size can be processed quickly and conveniently. The problem of determining the intertranslation relationship of the bilingual sentence pairs is converted into a binary classification problem by using the classification idea of the training classification model, so that the weights of the matching features of the bilingual corpus can be determined more scientifically and reasonably, and compared with the existing experience method, the universality is better, and the accuracy and the recall rate are improved accordingly.

Description

technical field [0001] The invention relates to a method for determining the mutual translation relationship of bilingual sentence pairs, especially a method and system for determining the mutual translation relationship of bilingual sentence pairs. Background technique [0002] The great value of corpus resources for natural language processing research has been increasingly recognized. Especially the parallel bilingual corpus, which is a special corpus that contains information about mutual translation between two languages. Parallel bilingual corpora can provide rich matching information between two languages, and have important application value in the acquisition of translation knowledge, the establishment of bilingual dictionaries, machine translation based on statistics or examples, word sense disambiguation, etc., especially high-quality The role of corpus is more prominent. [0003] There are two main ways to build a corpus, one is the traditional method of manual...

AI Technical Summary

Problems solved by technology

The feature threshold is set empirically, and the feature threshold may often be determined by the setter based on only a few corpus resources, which cannot cover the distribution of most corpora

Moreover, when the feature threshold set by experience is too low, the accuracy rate will drop, and if it is too high, the recall rate will drop.

Images