Text translation method, device, storage medium and computer equipment

Abstract

The invention relates to a text translation method. The method comprises the steps of obtaining a word sequence and a chapter text of a source text lacking pronouns; encoding the word sequence to obtain a source end vector sequence; decoding the source end vector sequence to obtain candidate translations, and target end vector sequences and translation scores corresponding to the candidate translations; respectively reconstructing the word sequence and the source end vector sequence with each target end vector sequence to obtain a reconstructed hidden layer vector sequence which corresponds toeach candidate translation and comprises word information of lacked pronouns; encoding the chapter text to obtain a chapter vector, and respectively fusing the chapter vector with each reconstructedhidden layer vector sequence to obtain a corresponding first fusion vector sequence; respectively carrying out reconstruction evaluation on the word sequence and each first fusion vector sequence to obtain a reconstruction score; and performing weighted summation on the translation score and the reconstruction score to obtain a comprehensive score, and screening a target translation from the candidate translations according to the comprehensive score. The translation quality can be improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a text translation method, device, storage medium and computer equipment, and a model training method, device, storage medium and computer equipment. Background technique [0002] Machine translation is to translate a 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 translation) by computer, so as to realize the Convert between text. Different languages ​​have different grammatical and sentence habits. For example, in languages ​​such as Chinese and Japanese, it is a very common phenomenon that the reference pronouns are missing. On the contrary, in English, French and other languages, the reference pronouns It is essential as a sentence component. When translating from a denotatively deficient language (such as C...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide a text translation method, device, computer-readable storage medium and computer equipment, as well as a model training method, device, computer-readable storage medium and computer equipment for the technical problem of low text translation accuracy

Images