Event extraction method and system based on attention mechanism

An event extraction and attention technology, applied in the field of information extraction, can solve problems such as low recall rate, error propagation, event trigger words cannot be used in downstream tasks, etc., and achieve the effect of wide application range and improved recall rate

Pending Publication Date: 2021-02-02
新华智云科技有限公司 +1
View PDF13 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the existing event extraction methods use a pipeline method in which event trigger words and event arguments are extracted separately, resulting in the propagation of the error rate of the two subtasks. At the same time, the characteristics of event trigger words cannot be applied to downstream tasks, resulting in a low accurate recall rate.

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 and system based on attention mechanism
  • Event extraction method and system based on attention mechanism
  • Event extraction method and system based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Embodiment 1, a kind of event extraction method based on attention mechanism, such as figure 1 shown, including the following steps:

[0053] S100. Constructing an extracted word prediction model:

[0054] S200, data preprocessing:

[0055] Obtain the text to be processed and its event type, extract the vector of each word in the text to be processed, obtain text vector data, extract the vector of each word in the event type, and generate event type vector data;

[0056] S300. Prediction of extracted words:

[0057] Inputting the text vector data and the event type vector data into the extracted word prediction model to obtain a tag sequence formed by tags corresponding to each word in the text to be processed;

[0058] The label is used to indicate whether the corresponding character belongs to the extracted word, and when it belongs to the extracted word, the position of the word in the extracted word and the category of the extracted word.

[0059] In this embodi...

Embodiment 2

[0106] Embodiment 2, an event extraction system, including a model building module and an extraction module:

[0107] The model construction module is used to use event trigger words and event arguments as extraction words, collect sample texts and event types thereof, and mark sample labels for each word corresponding to each extraction word in the sample texts; also use Extracting the vector of each word in the sample text to obtain a sample text vector, extracting the vector of each word in the event type to obtain a sample type vector; and the sample label training to obtain the extracted word prediction model;

[0108] The extraction module includes a preprocessing unit, a prediction unit and an extraction unit;

[0109] The preprocessing unit is used to obtain the text to be processed and its event type, extract the vector of each word in the text to be processed, obtain text vector data, extract the vector of each word in the event type, and generate event type vector da...

Embodiment 3

[0120] Embodiment 3. A computer-readable storage medium stores a computer program, and when the program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

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 and system based on an attention mechanism. The extraction method comprises the following steps: obtaining a to-be-processed text and an event type thereof, extracting a vector of each character in the to-be-processed text, obtaining text vector data, extracting a vector of each character in the event type, and generating event type vector data; inputting the text vector data and the event type vector data into a pre-constructed extracted word prediction model to obtain a label sequence formed by labels corresponding to each character in the to-be-processed text; and performing event extraction on the to-be-processed text based on the label sequence to obtain corresponding event trigger words and event arguments. By introducing the event type and combining the feature data corresponding to the event type to perform joint extraction on the event trigger word and the event argument, the accurate calling rate of event extraction is effectively improved.

Description

technical field [0001] The invention relates to the field of information extraction, in particular to an attention mechanism-based event extraction method and system. Background technique [0002] As a form of information, an event is defined as the fact that specific people and objects interact at a specific time and place, and its components include trigger words, event types, arguments, and argument roles; the target of event extraction That is to automatically complete the acquisition of the above information from unstructured information, and display it after it is structured. Event extraction is an important and challenging task in the field of information extraction, which can provide effective structured information for knowledge base construction, question answering, and language understanding tasks. [0003] Most of the existing event extraction methods use a pipeline method in which event trigger words and event arguments are extracted separately, resulting in th...

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): G06F40/289G06F40/216G06F16/35G06N3/04G06N3/08
CPCG06F40/289G06F40/216G06F16/35G06N3/049G06N3/084G06N3/045
Inventor 李明玉刘方然徐常亮贺大为
Owner 新华智云科技有限公司
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