Method for relationship classification with LSTM and CNN joint model based on location

A joint model and relationship classification technology, applied in biological neural network models, text database clustering/classification, instruments, etc., can solve problems such as interference and information redundancy, and achieve the effect of simple and clear algorithms and maximum information utilization

Active Publication Date: 2018-03-23
SHANDONG UNIV
View PDF5 Cites 108 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, inputting the state matrix into the convolutional neural network (CNN) in this

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
  • Method for relationship classification with LSTM and CNN joint model based on location
  • Method for relationship classification with LSTM and CNN joint model based on location
  • Method for relationship classification with LSTM and CNN joint model based on location

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] A joint location-based LSTM and CNN model for relation classification, figure 1It is the structural block diagram of the joint model of LSTM and CNN; the input layer is the input of the whole model, the second layer is the position feature vector layer, the third layer is the word vector layer, and the fourth layer is the connection layer, which combines the previously input word vector and position The vectors are connected, the fifth layer is the encoding layer, the network structure used in this layer is a bidirectional LSTM neural network, the output results of the encoding layer are he1 and he2, the sixth layer is the convolutional layer, and the network structure used in this layer is The convolutional neural network uses the output of the fifth layer as the input of the sixth layer (convolutional layer) for finer feature extraction. The seventh layer is a classifier, and the high-dimensional vector output by the convolutional layer is used by this The layer is tr...

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 relates to a method for relationship classification with an LSTM and CNN joint model based on location. The method includes the steps of (1) preprocessing data; (2) training word vectors; (3) extracting location vectors; acquiring the location vector feature and high-dimensional location feature vector of each word in a training set, cascading the word vector of each word with the high-dimensional location feature vector thereof to obtain a joint feature; (4) building a model for a specific task; encoding contextual information and semantic information of entities by use of bidirectional LSTM; outputting the vector of the location corresponding to the marked entities, inputting the output to CNN, outputting two entity nouns and their contextual information and relational wordinformation, and inputting the entity nouns and their contextual information and relational word information into a classifier for classification; (5) training the model by use of a loss function. The method does not need to manually extract any features, the joint model does not need to use additional natural language processing tools to preprocess the data, the algorithm is simple and clear, and the best effect at present is achieved.

Description

technical field [0001] The invention relates to a method for classifying relationships based on a position-based LSTM and CNN joint model, and belongs to the technical field of natural language processing. Background technique [0002] With the advent of the intelligent age, the processing method of big data is developing in the direction of automation and intelligence, and various jobs are gradually replaced by intelligent machines. There are more and more intersections between human society and intelligent machines. In such an era background Nowadays, intelligent and convenient human-computer interaction becomes more and more important. Therefore, the automatic construction technology of question answering system and knowledge base has received great attention and achieved some results in both industry and academia. These achievements are inseparable from the support of basic theories such as natural language processing, among which relation extraction plays an important ...

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
IPC IPC(8): G06F17/30G06F17/27G06N3/04
CPCG06F16/35G06F40/284G06N3/045
Inventor 李玉军王玥
Owner SHANDONG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap