Method and device for generating version and machine translation

Abstract

The present invention provides a translating method, a machine translating method, a translating device and a machine translating device. According to one aspect, the present invention provides the translating method; wherein, a first-language sentence to be translated is divided into a plurality of sections; a bilingual dictionary for alignment includes pairs of corresponding first-language and second-language example sentences and the alignment information of each pair of example sentences, as well as at least a translation section of each corresponding second-language translation of first-language sections. The method includes that the combination of second-language translation sections is optimally selected from the combination of a plurality of corresponding second-language translation sections to the first-language sentence according to the comprehensive score of the combination of the translation sections based on a plurality of feature functions, and the second-language translation is generated according to the optimal combination of the translation sections.

Description

technical field [0001] The present invention relates to information processing technology, in particular, to translation generation technology and machine translation (Machine Translation, MT) technology based on bilingual alignment technology. Background technique [0002] A machine translation system based on bilingual example sentences is an automatic translation system that directly uses aligned bilingual example sentences as translation knowledge. If there are more than input sentences to be translated, the translation system first uses matching technology to find matching bilingual example sentences from the aligned bilingual example sentence database, and then uses the alignment information of the bilingual example sentences to extract the translation segment corresponding to the matching segment from the bilingual example sentence. Finally, the translation system combines these translation segments to obtain a translation of the input sentence. [0003] At present, ...

AI Technical Summary

Problems solved by technology

[0008] Although the first method can find bilingual example sentences with similar semantics to the input sentence, it does not consider the transition between the translation segments when generating the translation.

As a result, the resulting translations are less fluent

[0009] The second method uses the language model of the target language to generate a translation. Although a translation with better fluency can be obtained, the semantic relationship between the input sentence and the bilingual example sentence is not considered when selecting the translation segment. Poor understanding

Images