Machine translation post-editing method and system

Abstract

The invention provides a machine translation post-editing method and system. The method comprises the following steps: training a machine translation model according to an original text in an original bilingual parallel corpus and a first translation of the original text; re-training the trained machine translation model according to the original text in the monolingual corpus and the translation of the original text in the monolingual corpus obtained in advance based on the machine translation engine; inputting the original text in the original bilingual parallel corpus into the re-trained machine translation model, outputting a second translation of the original text in the original bilingual parallel corpus, and training the post-editing model according to the second translation, the original text in the original bilingual parallel corpus and the first translation of the original text; and inputting the to-be-translated original text and a translated text of the to-be-translated original text obtained in advance based on the machine translation engine into the trained post-editing model, and outputting the edited translated text. According to the invention, the association relationship between the first translation and the second translation can be quickly learned by the post-editing model, and the convergence speed and the editing precision are high.

Description

technical field [0001] The present invention relates to the technical field of machine translation, in particular to a post-machine translation editing method and system. Background technique [0002] Post-editing is a very classic working mode of human translation. It mainly provides the original text to be translated, retrieves the result of machine translation, and the translator makes modifications and polishes on this basis, thereby improving the quality of translation. Most of the current translation aids provide support for this translation mode. The advantage of post-editing is that it reduces the translator's workload by providing a reference translation instead of starting from scratch. However, in actual work, when there is a large gap between the output of machine translation and the expected translation result, the post-editing mode often causes the translator to do a lot of boring revisions and edits. This further increases the translator's workload. [0003...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and system for editing after machine translation, which is used to solve the problem that the sample data obtained in the prior art cannot accurately establish the relationship between the translation of machine translation and the translation of automatic post-editing, resulting in poor performance after training and difficult Deficiencies in accurate editing of machine-translated translations to be edited, enabling accurate automatic post-editing of machine-translated translations

Images