Machine translation quality estimation method and device, equipment and storage medium

Abstract

The embodiment of the application provides a machine translation quality estimation method and device, equipment and a storage medium. The method comprises the steps: obtaining a source language textand a machine translation text; determining a first word feature vector set corresponding to the source language text and a second word feature vector set corresponding to the machine translation text; encoding the first word feature vector set to obtain a source language sentence vector corresponding to the source language text and an encoded first word feature vector set; processing the encodedfirst word feature vector set and second word feature vector set to obtain a target language sentence vector and target center word mixed bidirectional feature vector set; processing the source language sentence vector and the target language sentence vector to obtain alignment representation parameters; and processing the alignment representation parameter and the target center word mixed bidirectional feature vector set to obtain a machine translation quality estimation parameter. According to the embodiment of the appliction, the accuracy of the machine translation quality estimation parameter is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of machine translation, and in particular, to a method, device, device, and storage medium for estimating machine translation quality. Background technique [0002] Machine translation refers to the process of converting a natural source language into another natural target language through a machine translation model. Since the translation results given by different machine translation models are not the same, it is necessary to evaluate the quality of machine translation. [0003] In the related art, machine translation quality estimation (Quality Estimation, QE) is a technique for directly estimating the quality of machine translation. According to the granularity of text to be estimated, machine translation quality estimation can be divided into three levels: word level, sentence level, and chapter level. The true value of the sentence-level machine translation quality estim...

AI Technical Summary

Problems solved by technology

[0004] However, in the above-mentioned process of determining the quality estimation parameters of machine translation, the participation of the source language text in the estimator is low, so that the accuracy of the final quality estimation parameters of machine translation is low

Images