Method and system for deep nerve translation based on character encoding

Abstract

The invention provides a method and a system for deep nerve translation based on character encoding. A combined nerve network model is established by using an RNN to cover the whole translation process, and translation tasks are directly completed from the perspective of an encoder-decoder framework. The method comprises the following steps: A, word vector generation: performing word segmentation on character-level input data through neural network modeling and generating a word vector; B, language model generation: establishing grammar rules by utilizing the characteristic of memory of the recurrent neural network in time; C, word alignment model generation: obtaining the probability of translating multiple words in a source language statement into target language words; D, output: translating an inputted source language into a target language; E, translation model combination: establishing a deep nerve translation model (RNN-embed) based on character encoding in combination with neural network models in the four steps and accelerating model training by using CPU parallel computation.

Description

technical field [0001] The invention relates to the technical field of machine translation, in particular to a method and system for deep neural translation based on character coding. Background technique [0002] Machine translation is often called automatic translation technology. By using the programming ability of computers, one language is automatically converted into another language. The former is called the source language and the latter is called the target language. Today, the broad prospects of the subject of machine translation have been recognized, and there is no doubt that it will be a hot spot of applied technology. [0003] At present, machine translation can be divided into rule-based and corpus-based methods as a whole. Among them, the rule-based method has been studied to the syntactic stage, but its application in the general field is not strong, and it is often limited to specialized fields. There are applications. The corpus-based method can be subdi...

AI Technical Summary

Problems solved by technology

[0004] However, the traditional statistics-based machine translation model has the following problems: First, we need to preprocess the source language and target language, which is prone to high-dimensional and sparse data problems; each module in the translation model is relatively independent, which increases the difficulty of training ; After the model is generated, if there are uncommon words, it needs to be reprocessed, destroying the integrity of the model

Images