Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text relation extraction method based on double-layer attention mechanism and bidirectional GRU

A relation extraction and attention technology, applied in neural learning methods, unstructured text data retrieval, text database clustering/classification, etc. performance, improve accuracy

Active Publication Date: 2019-11-26
THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
View PDF5 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, RNN, CNN and LSTM cannot make full use of the local features and global features of text information

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
  • Text relation extraction method based on double-layer attention mechanism and bidirectional GRU
  • Text relation extraction method based on double-layer attention mechanism and bidirectional GRU
  • Text relation extraction method based on double-layer attention mechanism and bidirectional GRU

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0062] This embodiment verifies the effect of the present invention through specific experiments. The experimental data set is based on the military corpus of Baidu Encyclopedia and Interactive Encyclopedia, and is generated through manual annotation. The dataset includes 13940 training samples and 2390 test samples, including 24 relationships.

[0063] Such as figure 1 As shown, the specific steps of relation extraction are as follows:

[0064] S1: Carry out manual labeling of entity and relational data, specifically as figure 2 shown.

[0065] S2: Preprocess the labeled data to generate the training set and test set of the entity extraction model and the relationship extraction model:

[0066] Convert the entity labeling data to the BMES entity labeling system. B indicates the starting position of the entity, M indicates the middle part ...

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 text relation extraction method based on a double-layer attention mechanism and a bidirectional GRU. The text relation extraction method comprises: carrying out entity labeling and relation labeling text corpora; preprocessing the annotation data to generate a training set and a test set of an entity extraction model and a relationship extraction model; constructing a relationship extraction network; respectively carrying out entity extraction model training and relationship extraction model training; inputting the test set data into an entity extraction model to obtain an entity identification result; and inputting the entity identification result and the test set data into a relationship extraction model to obtain a relationship extraction result. According to the invention, entity position information and entity label information are utilized to expand word vector characteristics; vectorization of text information is realized, more feature information is provided for relationship identification, the correlation between input information and output information of the bidirectional GRU model is improved, the influence of keywords on output is enhanced, the anti-noise capability is improved, and the Chinese text relationship extraction accuracy can be effectively improved.

Description

technical field [0001] The invention relates to a text relation extraction method, in particular to a text relation extraction method based on a double-layer attention mechanism and a bidirectional GRU. Background technique [0002] With the rapid development of information technology and the rapid increase of information volume, how to efficiently extract effective information from unstructured text information has become a hot spot of concern. Text information extraction includes entity extraction, relationship extraction and event extraction. Relation extraction is one of the basic tasks of natural language processing, which is used to identify the relationship between two named entities in text information. Through relationship extraction, a triple structure of entity 1, relationship and entity 2 can be formed. This plays an important role in subsequent applications such as Chinese information content retrieval and knowledge graph construction. [0003] Relationship e...

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): G06F17/27G06F16/35G06N3/04G06N3/08
CPCG06F16/35G06N3/049G06N3/08G06N3/045Y02D10/00
Inventor 王鑫鹏李晓冬吴蔚徐建平
Owner THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com