Structured text translation method and device

Abstract

The embodiment of the invention provides a structured text translation method and device, and the method comprises the steps: removing a structured mark of a to-be-translated target structured text, and obtaining a target text; inputting the target text into a trained text translation neural network model, and performing search translation on the translation candidate words of the target text according to a phrase search space to obtain a target translation text and alignment information; and according to the alignment information, performing structured mark recovery processing on the target translated text to obtain a target structured translated text. According to the embodiment of the invention, the structured mark of the structured text is removed; therefore, the text with the structural mark removed is translated through the neural network model based on the phrase search space, the translated text is restored to the structural mark, the structured translated text is obtained, andthe translated text is translated through the neural network model.

Description

technical field [0001] The invention relates to the technical field of machine translation, in particular to a structured text translation method and device. Background technique [0002] In recent years, the rapid development of neural network machine translation technology has significantly improved the quality of machine translation. Furthermore, the improvement of the quality of machine translation has also made it widely used in real life. [0003] Although neural machine translation is excellent in translating plain text, it still cannot be well applied to translating structured text, because the translation of structured text needs to satisfy structural constraints, for example, the source end is between a pair of HTML tags The translation corresponding to the content of the target must also be included between the same pair of HTML tags, but because in the existing neural machine translation, there is no structured text corpus for training the model for structured t...

AI Technical Summary

Problems solved by technology

[0003] Although neural machine translation is excellent in translating plain text, it still cannot be applied to translating structured text well, because the translation of structured text needs to satisfy structural constraints, for example, the source end is between a pair of HTML tags The translation corresponding to the content of the target must also be included between the same pair of HTML tags, but because in the existing neural machine translation, there is no structured text corpus for training the model for structured text translation; and , neural machine translation lacks explicit alignment information and cannot add structural constraints, making it difficult for existing neural machine translation to translate structured text

Images