Multi-task interaction enhanced electronic text event extraction method

A technology of event extraction and electronic text, applied in neural learning methods, electronic digital data processing, instruments, etc., can solve problems such as poor event extraction effects, achieve easy learning, improve overall performance, and improve results

Pending Publication Date: 2020-12-11
WUHAN UNIV
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention proposes an electronic text event extraction method enhanced by multi-task interaction, which is used to solve or at least partially solve the technical problem of poor event extraction effect existing in the prior art method

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
  • Multi-task interaction enhanced electronic text event extraction method
  • Multi-task interaction enhanced electronic text event extraction method
  • Multi-task interaction enhanced electronic text event extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The inventors of the present application found through a lot of research and practice that most of the existing joint event extraction models only combine the trigger word recognition task and the argument role prediction task, ignoring the entity recognition task and the other two subtasks. connect. However, there are still some defects in the existing event extraction model that combines three sub-tasks: 1. The essential difference between the trigger word recognition task and the entity recognition task is not considered, and the same set of shared parameters is used for feature representation; 2. The sentence-level information that is easier to learn is not fully utilized; 3. The information interaction between multiple subtasks is not sufficient, and the communication method is not established according to the characteristics of the subtasks.

[0032] In view of the above defects, the present invention proposes an interaction-enhanced multi-task joint electronic te...

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 provides a multi-task interaction enhanced electronic text event extraction method, which is a method for extracting an event from an electronic text, combines three tasks of an entity recognition task, a trigger word recognition task and argument role prediction, and additionally introduces an auxiliary event sentence recognition task. Therefore, the attention of the extractor is more focused on the event sentence. According to the method, two sets of parameters are adopted for modeling an entity recognition task and a trigger word recognition task respectively, and informationinteraction is added between sub-tasks, so that a plurality of sub-tasks can be cooperatively trained to realize excellent performance. According to the combined event extraction method, a neural network technology is adopted, a more direct, complete and end-to-end event extraction model is formed, and the effect of an event extraction task is greatly improved.

Description

technical field [0001] The invention relates to the technical field of event extraction and multi-task learning, in particular to an electronic text event extraction method with multi-task interaction enhancement. Background technique [0002] With the rapid development and widespread popularization of the Internet, a large amount of information is presented to people in the form of electronic text. Quickly and accurately mine these information, extract the event-related information that people are interested in, and convert it into a semi-structured or structured form, which is the event extraction task (event extraction, EE). Event extraction is an important task in the field of natural language processing, and has a wide range of applications in information retrieval, question answering systems, summarization systems and other fields. The event extraction task can be divided into three subtasks, including entity mentions detection (EMD), trigger word recognition (event d...

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): G06F40/284G06F40/295G06F40/30G06N3/04G06N3/08
CPCG06F40/284G06F40/295G06F40/30G06N3/08G06N3/047
Inventor 钱铁云唐小雅陈壮
Owner WUHAN 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