Event detection method and device based on hybrid attention network

A technology of event detection and attention, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as low accuracy, limited method performance, low recall rate, etc., to alleviate data sparsity and natural language ambiguity , improve the effect of the effect

Active Publication Date: 2021-02-02
NAT UNIV OF DEFENSE TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although the current research on event detection problems has made relatively great progress, there are still two problems that will seriously limit the performance of current methods
One is the low recall rate problem due to data sparsity
In the case of limited training data, there are especially few training examples for some event types. The model learned from these few training examples needs to identify the correct event type f

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 detection method and device based on hybrid attention network
  • Event detection method and device based on hybrid attention network
  • Event detection method and device based on hybrid attention network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0046]Example one

[0047]Such asfigure 1 As shown, an event detection method based on a hybrid attention network, the method includes:

[0048]Step 1. Construct a hybrid attention network model, including a multi-language presentation layer, a hybrid attention layer and a classification layer;figure 2 Shown

[0049]Step 2: Perform translation of the source text and acquisition of target text in multiple languages ​​in the multilingual presentation layer, and perform text alignment to convert the target text in multiple languages ​​into a vector representation of a sentence sequence;

[0050]Step 3. At the hybrid attention layer, concurrently conduct contextual attention learning for texts in multiple languages ​​at the same time, and perform cross-source language and multiple target language information fusion through a multilingual attention mechanism;

[0051]Step 4. Perform predictive classification of event types at the classification layer.

[0052]The following will introduce the entire model ...

Example Embodiment

[0082]Example two

[0083]The invention also discloses an electronic device, including:

[0084]processor;

[0085]And, a memory is used to store executable instructions of the processor;

[0086]Wherein, the processor is configured to execute the aforementioned event extraction method by executing the executable instruction.

[0087]In order to evaluate the effectiveness of HAN's use of multilingual clues to improve the effect of event detection, English is used as the source language in this embodiment, and it is performed on two benchmark data sets, ACE2005 and TAC KBP 2015 event block detection evaluation data set (KBPEval2015) experiment. For the ACE2005 data set, use the same experimental settings as the previous experiments, that is, 529 / 30 / 40 documents are used as the training set / development set / test set. For the KBPEval2015 data set, we test the model on the provided evaluation data set (LDC2015R26), using the previous RichERE labeled data set (LDC2015E73) as the training set, except for...

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 detection method and a device based on a hybrid attention network, and the method comprises the steps: constructing a hybrid attention network model which comprises amulti-language representation layer, a hybrid attention layer and a classification layer; performing translation of a source text and acquisition of a target text of multiple languages on the multi-language representation layer, performing text alignment, and converting the target text of multiple languages into vector representation of a sentence sequence; using the hybrid attention layer for carrying out context attention learning on texts of multiple languages in parallel and carrying out information fusion of cross-source languages and multiple target languages through a multi-language attention mechanism; and performing prediction classification of event types in the classification layer.

Description

technical field [0001] The invention relates to the technical field of event detection in natural language processing, in particular to an event detection method and device based on a hybrid attention network. Background technique [0002] The task of event detection is to identify event instances of a specific type from plain text. Specifically, given an input text, the event detection task needs to determine the trigger words contained in the text and the type of event described by the trigger words, which includes two subtasks of event trigger word identification and event trigger word classification. For example, given a plain text: Three elephants were shot dead. Event detection can automatically identify the trigger word "shot" and its triggered event subtype Attack (type Confict) and the trigger word "dead" and its triggered event subtype Die (type Life) from the text. [0003] Although the current research on event detection problems has made relatively great progre...

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): G06F40/205G06F40/58G06F40/151G06N3/04G06N3/08
CPCG06F40/205G06F40/58G06F40/151G06N3/08G06N3/045
Inventor 谭真黄培馨赵翔方阳徐浩唐九阳肖卫东张鑫
Owner NAT UNIV OF DEFENSE 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