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

Event extraction method based on sequence labeling

A technology of event extraction and sequence labeling, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve problems such as incomprehension by machines, limited representation ability, long-distance dependency modeling, etc., to avoid propagation errors, optimize Identify the effect of the effect

Inactive Publication Date: 2018-03-13
成都蓝景信息技术有限公司
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A common problem is that most data are initially unstructured, such as text described in natural language, making it difficult for machines to directly understand
In this way, errors in named entity recognition will affect the judgment of events
Second, most of the existing work mostly uses N-gram models (N is generally not greater than 3), which cannot model long-distance dependencies.
Traditional methods to solve NLP problems use shallow models and high-dimensional, extremely sparse feature vectors, with limited representation capabilities

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
  • Event extraction method based on sequence labeling
  • Event extraction method based on sequence labeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The following will be combined with Figure 1-Figure 2 The present invention is described in detail, and the technical solutions in the embodiments of the present invention are clearly and completely described. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0020] The present invention provides an event extraction method based on sequence labeling through improvement. When implemented, event extraction from unstructured data can benefit information extraction systems in various ways. For example, personalized news recommendations can be made to users based on user preferences and identified events. In addition, event extraction is very helpful for risk analysis systems, public opinion mon...

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 an event extraction method based on sequence labeling. The vent extraction method comprises the following several steps that 1, input texts are preprocessed; 2, word sequencesof the texts are labelled by utilizing an LSTM+CRF network; 3, labeling results are merged to obtain event elements; 4, a designed template is filled with extracted events and their elements to form one-sentence description. The method mainly solves the problem how to extract events of loans, consolidations and the like from announcements of various major events of listed companies and give descriptions in a human language form. The labor cost for reading a large number of company announcements every day by financial employees is saved.

Description

technical field [0001] The invention relates to an event extraction method, in particular to an event extraction method based on sequence labeling. Background technique [0002] With the growth of data and the explosion of digital media information, information extraction becomes more and more important and difficult. A common problem is that most data are initially unstructured, such as text described in natural language, making it difficult for machines to understand directly. This makes automatic information retrieval and information extraction difficult when the amount of data is particularly large. Information extraction in a narrow sense is text mining, which uses NLP (Natural Language Processing) technology to extract information from texts from different sources such as news and blogs, and store them in a structured manner. As a kind of information extracted from the text, events represent the behavioral relationship between entities at a specific time and space. ...

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): G06F17/27G06F17/30
CPCG06F16/337G06F40/295
Inventor 赵二超韩伟
Owner 成都蓝景信息技术有限公司
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