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

Biomedical entity relationship classification method based on a context vector graphic kernel

A biomedical and entity-relationship technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as low extraction performance

Inactive Publication Date: 2019-06-11
DALIAN JIAOTONG UNIVERSITY
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the problem of low performance of relation extraction in long texts in scientific literature, this method starts from the graph representation of sentences and aims to make full use of context information, and proposes a method based on context vector graph kernel for biomedical entity relation classification

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
  • Biomedical entity relationship classification method based on a context vector graphic kernel
  • Biomedical entity relationship classification method based on a context vector graphic kernel
  • Biomedical entity relationship classification method based on a context vector graphic kernel

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] Based on the above description of specific implementations of the method and system involved in the present invention, description will be made in conjunction with specific embodiments.

[0040] This embodiment uses two data sets in the DDIExtraction 2013 challenge, namely Medline and ALL-2013, and ALL-2013 is the union of the two data sets of Medline and DrugBank. These two datasets are divided into training set and test set. Medline is derived from texts in biomedical abstracts in the Medline database, and its training and testing sets contain 1787 and 496 relational instances, respectively. The Medline dataset not only has fewer samples, but also has many compound long and complex sentences. The training and test sets of ALL-2013 contain 27,792 and 5,761 relation instances, respectively. Sentences in DrugBanK are derived from texts in the biomedical database DrugBank. The specific steps of the biomedical entity relationship classification method based on the conte...

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 biomedical entity relationship classification method based on a context vector graphic kernel, belongs to the technical field of biomedical text mining and data mining, and solves the problem of biomedical entity relationship classification in biomedical articles. The method comprises the following steps: S1, carrying out text processing on biomedical documents; S2, performing structured representation on the sentences; S3, constructing a context vector; S4, constructing equivalent class division based on context vectors; S5, extracting a context vector kernel and features based on the equivalent class; S6, normalizing the weight of the feature; S7, constructing a biomedical entity relationship classification model; And S8, predicting the biomedical entity relationship in the biomedical literature. The method has the effect that the biomedical entity relationship in the biomedical article with the small corpus, long complex sentences and many sentences can beefficiently classified.

Description

technical field [0001] The invention relates to the technical field of biomedical text mining and data mining, in particular to a biomedical entity relationship classification method based on context vector graph kernels. Background technique [0002] Relationship extraction between biomedical entities is the most basic and core task in the field of biomedicine. It not only helps to build biomedical related databases, but also is one of the most basic and critical links in the construction of knowledge graphs. Massive biomedical literature contains rich and cutting-edge biomedical knowledge, which is an important knowledge repository for researchers in the field of biomedicine. Practice has shown that the application of text mining technology can automatically and efficiently extract useful knowledge from this knowledge repository , but there are still many deficiencies in the performance and application of the existing methods. [0003] Since entity relationship classific...

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): G06F16/28G06F17/27
Inventor 郑巍林鸿飞
Owner DALIAN JIAOTONG UNIVERSITY
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