A machine translation method and device based on feature stem extraction

Abstract

The invention relates to a machine translation method and device based on characteristic sentence stem extraction. Specifically, the method comprises the steps of 1), obtaining multiword sequences ina language A corpus, and identifying the sequences of which structures satisfy a sentence stem demand; 2), on the basis of internal adhesive force, external boundary independence and text distributiondomains, determining characteristic sentence stems, and screening the characteristic sentence stems based on a MIN-MAX normalization algorithm and a local maximum duplication elimination method; 3),translating the characteristic sentence stems to obtain a characteristic sentence stem database; and 4), inputting a to-be-translated language A text, extracting sentence stems sentence by sentence, searching sentence stem translations in the characteristic sentence stem database, translating words and expressions except for the sentence stems, and combining the translations of the words and expressions with the sentence stem translations according to word orders of a target language B, thereby obtaining translations. The device comprises a characteristic sentence stem database unit, a language input unit, a sentence stem extraction unit, a sentence stem identification unit, a translation unit and a combination unit. The machine translation method and device provided by the invention are high in translation efficiency and short in processing time and have wide application prospect.

Description

technical field [0001] The invention belongs to the field of machine translation, and relates to a machine translation method and device based on characteristic sentence stem extraction, in particular to a machine translation method and device based on a corpus to extract characteristic sentence stems. Background technique [0002] From early dictionary matching to rule-based translation of dictionaries combined with linguistic expert knowledge, to corpus-based statistical machine translation, with the improvement of computer computing power and the explosive growth of multilingual information, machine translation technology has gradually stepped out of the ivory tower and started Provide real-time and convenient translation services for ordinary users. [0003] The method of machine translation based on corpus has become the main direction of research in the field of machine translation. It is against this background that the corpus-driven translation equivalence research ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the defects of low quality and low accuracy in the translation of cross-lingual texts in the prior art, and provide a kind of feature sentence stem extraction that is accurate, has a small amount of processing, and has good quality and high accuracy in translating cross-language texts. Machine translation method and device based on characteristic sentence stem extraction

Images