Text translation method, device, storage medium and computer device

Abstract

The invention relates to a method, device, a readable storage medium and a computer device for text translation, including steps: obtaining an initial source text and reconstructing that source text,wherein the reconstructed source text is the source text obtained by supplementing the initial source text with missing word position information; carrying out semantic coding on the initial source text to obtain a source end vector sequence corresponding to the initial source text; a target end vector being obtained by sequentially decoding that source end vector sequence, and the target end vector being decoded according to the word vector of the candidate target word determined before each decoding, and the candidate target word of the current time being determined according to the target end vector of the current time; forming a target end vector sequence by sequentially decoding the target end vectors; performing reconstruction evaluation processing on the source vector sequence and the target vector sequence according to the reconstruction source text to obtain a reconstruction score corresponding to each candidate target word; a target text being generated according to that reconstruction score and the candidate target word. The scheme provided by the present application can improve the quality of translation.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a text translation method, device, computer-readable storage medium and computer equipment. Background technique [0002] Machine translation refers to the translation of one natural language text (the natural language text to be translated is generally called the source text) into another natural language text (the translated natural language text is called the target text) by computer to achieve different languages. conversion between texts. Different languages ​​have different grammar and sentence habits. For example, in languages ​​such as Chinese and Japanese, the lack of pronouns is a very common phenomenon. On the contrary, in languages ​​such as English and French, pronouns are used as sentences. Ingredients are essential. When translating from a pronoun-absent language (such as Chinese) to a non-pronoun-absent language (such as English), the implicit...

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a text translation method, device, computer-readable storage medium and computer equipment for the technical problem of low text translation accuracy

Images