Chinese language processing model and method based on deep neural network

A deep neural network and language processing technology, applied in the field of Chinese language processing models, can solve problems such as Chinese language processing incompatibility

Active Publication Date: 2019-08-30
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, Chinese natural language processing studies the representation and application of Chinese language. In the field of natural language processing using neural networks, there are often strict requirements on the length of input sequences and output sequences, which is not consistent with Chinese language processing in practical applications. conform to

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Chinese language processing model and method based on deep neural network
  • Chinese language processing model and method based on deep neural network
  • Chinese language processing model and method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The present invention will be further described below in conjunction with the accompanying drawings.

[0069] Such as figure 1 As shown, the Chinese language processing model based on the deep neural network provided in this embodiment includes three parts: a semantic encoding network, a part-of-speech analysis network and a semantic decoding network. The processing flow is divided into two stages of encoding and decoding, the semantic encoding network, the part-of-speech analysis network is responsible for the encoding stage, and the semantic decoding network is responsible for the decoding stage.

[0070] The coding stage specifically includes the following steps:

[0071] Step 1: Preprocessing the Chinese text to be processed. First, the Chinese source text is segmented into words, and the word vector generation method is used to generate the Chinese word vector sequence X=x after the word segmented data 1 , x 2 , x 3 ,...,x M . M is the data length of the sou...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a Chinese language processing model and method based on a deep neural network, and the model comprises three parts of a semantic coding network, a part-of-speech analysis network, and a semantic decoding network, wherein the semantic coding network and the part-of-speech analysis network are connected through an attention network and the semantic decoding network. The semantic coding network and the part-of-speech analysis network firstly process the word vectors generated by a source text, the semantic coding network outputs a semantic information vector of the sourcetext, and the part-of-speech analysis network outputs a part-of-speech information vector of the source text and connects the semantic information vectors and the part-of-speech information vectors ina concat () mode to serve as the input of the attention network, the attention network generates the background vectors containing all information of the source text according to the input information to serve as the input of the semantic decoding network, and the semantic decoding network calculates according to the background vector to obtain the probability distribution of all candidate words,and outputs each element of the target text one by one according to the probability distribution, so that the text mapping accuracy and the system performance are improved.

Description

technical field [0001] The invention relates to a Chinese language processing model and method based on a deep neural network, and belongs to the technical field of natural language intelligent processing. Background technique [0002] At present, the research of natural language processing is a model that can perform language representation and language application, establish a computing framework to realize such a language model, and propose various methods to improve this model, design various practical systems based on this model, and explore these practical systems. System evaluation techniques. [0003] The ultimate goal of natural language processing is to allow machines to understand and generate natural language, specifically, to study a cognitive machine that humans can communicate with in their own language. However, Chinese natural language processing studies the representation and application of Chinese language. In the field of natural language processing usin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27G06N3/04G06N3/08
CPCG06N3/08G06F40/289G06F40/30G06N3/045
Inventor 王玉峰张江
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products