English lexical analysis method and system for neural network machine translation

Abstract

The invention provides an English lexical analysis method for neural network machine translation. The English lexical analysis method comprises the following steps: performing English word segmentation on a to-be-processed English text; carrying out query screening on each word obtained after English word segmentation by utilizing a special vocabulary; reserving result information of the queried words in a lexical analysis result; performing rule processing on the words which are not queried; carrying out word architecture restoration on the words meeting the rule processing conditions, and directly storing the words which do not meet the rule processing conditions in a lexical analysis result; and outputting a lexical analysis result, and adding the lexical analysis result into machine deep learning training. The invention further provides an English lexical analysis system for neural network machine translation. According to the English lexical analysis method for neural network machine translation, the problems that the machine learning efficiency is reduced and the translation quality is poor due to the fact that training corpus data of neural network machine translation is sparse can be solved.

Description

technical field [0001] The invention belongs to the technical field of language processing, and in particular relates to an English lexical analysis method and system for neural network machine translation. Background technique [0002] Neural network machine translation technology has been proposed in recent years and has quickly become the mainstream research method in the field of machine translation. Compared with traditional machine translation technology, its outstanding feature is to combine the advantages of neural network and deep learning to overcome the grammatical inconsistencies caused by segment-based translation. Accurate, language is not smooth, can make full use of context information, make the translation smooth, high accuracy, and high engineering efficiency. [0003] However, in the process of machine translation of English texts, since English belongs to the inflectional language family, words have multiple forms such as singular and plural, active and p...

AI Technical Summary

Problems solved by technology

[0010] For this reason, what the present invention is to solve is that the training corpus data of the neural network machine translation in the prior art is sparse, which causes the machine learning efficiency to decline and the problem of poor translation quality, and then provides a kind of English lexical analysis for neural network machine translation method and system

Images