Dependency graph network-based Han-Vietnamese neural machine translation method

Abstract

The invention relates to a dependency graph network-based Han-Vietnamese neural machine translation method, and belongs to the technical field of natural language processing. The method comprises thefollowing steps: firstly, crawling Chinese-Vietnamese parallel corpora ar from a website, and performing dependency syntax analysis on the obtained Chinese-Vietnamese bilingual corpora through a dependency syntax analysis tool; secondly, converting the obtained source language dependency syntax parsing tree into a dependency graph by using a graph encoder, encoding the dependency graph to obtain dependency graph structure information, sending the dependency graph structure information to an encoding end to be fused with source language sequence information, and sending the fused information toa decoding end to guide a model to translate. According to the invention, the dependency relationship is converted into the dependency graph by fusing the dependency syntax information, and the graphneural network is utilized to realize global structural coding of the dependency graph, so that richer global dependency information is provided for the translation model, and certain help is provided for improving the translation effect of the Han-Van language pairs with syntax differences.

Description

technical field [0001] The invention relates to a Chinese-Vietnamese neural machine translation method based on a dependency graph network, and belongs to the technical field of natural language processing. Background technique [0002] Chinese-Vietnamese neural machine translation is a low-resource machine translation task. Due to the lack of large-scale parallel sentence pairs, the translation performance is not good. Chinese and Vietnamese belong to different language families, and their syntax is relatively different. There is a difference between the preposition and the postposition of attributives. In the comparison of Chinese and Vietnamese bilingual word alignment, Chinese attributives are generally located in front of the modified terms, such as "beautiful" as The attributive modifies "singer", and "beautiful" is used as an attributive to modify "singing voice". In the syntactic structure of Vietnamese, the attributive is generally located after the modified word, ...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a Chinese-Vietnamese neural machine translation method based on a dependency graph network to solve the problem that in low-resource scenarios, due to the lack of large-scale parallel corpus, the translation model may not be able to fully learn bilingual syntactic differences, and cannot model deep layers Syntactic structure information, resulting in out-of-order translations and poor translation performance

Images