Translation model establishing method and system

Abstract

The invention discloses a translation model establishing method and system. The translation model establishing method comprises the following steps: respectively generating a regular alignment table, a word semantic vector table and a phrase table according to alignment information of a double-language parallel corpus, subsequently generating a source language phrase semantic vector table of a source language semantic space and a target language phrase semantic vector table of a target language semantic space by using the word semantic vector table and the phrase table, and finally training by using phrase semantic vector tables of different semantic spaces, thereby generating a translation model integrated with semantic information. The result shows that phrase semantic information can be integrated in statistic machine translation, the research shows that the relevance of words or phrases to context words or phrases can be reflected in the semantic information, and compared with a conventional translation method based on words or phrases, the translation model is relatively high in translation quality after the phrase semantic information is integrated, so that the translation property of the statistic machine translation is further improved as compared with that of the prior art.

Description

Technical field [0001] The invention belongs to the technical field of statistical machine translation, and in particular relates to a method and system for constructing a translation model. Background technique [0002] In recent years, with the improvement of computing power and the continuous enrichment of corpus resources, statistical machine translation technology has gradually become the most important research hotspot in the field of natural language processing. [0003] The realization of statistical machine translation usually includes two main processes: training and decoding. The so-called training refers to training a statistical translation model from corpus resources according to a certain algorithm; the so-called decoding or translation refers to the translation of the text to be translated according to the trained translation model. The initial statistical machine translation method was established based on the noise channel model. Later, in practice, the researche...

AI Technical Summary

Problems solved by technology

The initial statistical machine translation method was established based on the noise channel model. Afterwards, researchers further generalized the model in practice and proposed a statistical machine translation method based on the idea of ​​maximum entropy. On this basis, the statistical machine translation method is also The development based on words, phrases and syntax has improved the performance of machine translation more or less, that is, compared with the previous translation models, the translation performance of translation models based on words, phrases or syntax has improved to a certain extent. However, it is still far away from realizing the translation goal of "credibility, expressiveness and elegance".

Images