Machine translation method based on blocking mechanism

Abstract

The invention discloses a machine translation method based on a blocking mechanism and belongs to the technical field of machine translation. The method comprises the following steps of S1, convertinga to-be-translated statement into a vector corresponding to the to-be-translated statement through utilization of a blocking encoder; and S2, decoding the vector corresponding to the to-be-translatedstatement through utilization of a decoder, and generating a machine translation result corresponding to the to-be-translated statement through utilization of a Beam Search algorithm based on a language model. According to the method, the problem that long sentence translation defect, readability defect and translation omission defect exist in the translation result due to the fact that the existing machine translation based on a reply type neural network is relatively long in statement, independent in word and expression and misaligned in rigid word is solved, and a machine translation effect is improved.

Description

technical field [0001] The invention relates to the field of machine translation, in particular to a machine translation method based on a block mechanism. Background technique [0002] Translation is the process of converting source language sentences into target language sentences. It is an important means to break through the barriers between different languages, and it is very important in the communication between different cultures. With the development of society, people's demand for translation has increased significantly, human translation is not enough to meet the demand, and the demand for machine translation has increased and its importance has become prominent. [0003] Neural network-based machine translation methods directly use neural networks to model translation in an end-to-end manner, including reply-based neural networks, convolutional neural networks (Convolutional Neural Network, CNN) and feedforward neural networks (Feedforward Neural Network), etc. ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is: the present invention provides a machine translation method based on the block mechanism, which makes up for the existing machine translation based on the reply neural network, which causes long translation results due to long sentences, independent words and poor word alignment. Sentence Translation Defects, Readability Defects and Omission Defects

Images