Literature-based cancer-related biomedical event database construction method

A biomedical and cancer-related technology, applied in text database indexing, unstructured text data retrieval, electronic digital data processing, etc., can solve problems such as the inability to fully capture long-distance contextual semantic information and the inability to fully express syntactic features.

Active Publication Date: 2020-10-30
DALIAN UNIV OF TECH
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides a biomedical entity relationship joint extraction model based on an entity relationship graph, and a biomedical event extraction system based on a hierarchical distillation network, which solves the problem that the existing research cannot fully capture the long-distance contextual semantic information and cannot fully express syntactic features to improve the accuracy of event extraction, thereby constructing a cancer-related fine-grained biomedical event database

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
  • Literature-based cancer-related biomedical event database construction method
  • Literature-based cancer-related biomedical event database construction method
  • Literature-based cancer-related biomedical event database construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087] The system of the present invention can perform automatic word representation, biomedical entity and entity relationship extraction, and biomedical event extraction for a given text, which greatly facilitates researchers to analyze biomedical events described in documents from a large number of documents. The system adopts B / S (Browser / Server, browser / server mode, uses the Django framework to build the system, mainly implemented with HTML, CSS and other technologies) structure design, and is divided into three parts: view layer, logic layer and data layer. As shown in table 2:

[0088] Table 2 Database system structure

[0089]

[0090] 1. The user enters the text to be parsed

[0091] Text input supports keyboard input and uploading local files. The view layer accepts the text to be retrieved input by the user, submits it to the logic layer, and stores it in the data layer. Suppose the text to be analyzed by the user is "We have used retroviral-mediated gene deliv...

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 belongs to the technical field of natural language processing, and provides a literature-based cancer-related biomedical event database construction method, which consists of three parts: 1, entity relationship graph-based biomedical entity and entity relationship joint extraction; 2, biomedical event extraction based on a layered distillation network; and 3, a cancer-related biomedical event database construction. On the basis of a traditional method, the characteristics of entities and contexts in a biomedical text are fully considered. The problems of multi-type entity identification and incomplete entity identification in biomedical event extraction are solved. Deeper syntax information is obtained based on a layered distillation network to extract the biomedical event. The complex event extraction precision is improved, researchers in the biomedical field can be helped to automatically analyze texts, a function of retrieving known biomedical named entities and biomedical events can be provided, and the researchers can be helped to research and analyze biomedical related literatures.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and relates to a method for high-quality biomedical named entity recognition, entity relationship extraction, and biomedical event extraction for biomedical related documents, specifically refers to a method based on an Entity-Relation Graph , ERG) biomedical entity and entity relationship joint extraction, and biomedical event extraction based on Hierarchical Distillation Network (HDN). Background technique [0002] The biomedical event database stores complete biomedical events. Biomedical events are composed of trigger words and elements, where trigger words are generally verbs or gerunds, and elements are generally trigger words of biomedical entities or another event. The construction of the biomedical event database involves three steps: Word Representation, Biomedical Named Entity Recognition and Entity Relationship Extraction, and Biomedical Event Extraction. [0003]...

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): G06F40/279G06F16/31G06N20/00
CPCG06F40/279G06F16/31G06N20/00
Inventor 李丽双连瑞源黄梦佐王泽昊袁光辉
Owner DALIAN UNIV OF TECH
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