Event recognition method and system based on probabilistic soft logic psl

A recognition method and soft logic technology, applied in character and pattern recognition, computer components, special data processing applications, etc., can solve problems such as ignoring global information, and achieve improved recognition accuracy, accurate and reliable event recognition, and accurate clustering Effect

Active Publication Date: 2017-10-27
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitations of classifiers, traditional techniques almost only utilize local information near candidate words, ignoring global information at the text level and corpus level, which are crucial for event recognition

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 recognition method and system based on probabilistic soft logic psl
  • Event recognition method and system based on probabilistic soft logic psl
  • Event recognition method and system based on probabilistic soft logic psl

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0056] figure 1 It is a flow chart of Embodiment 1 of the event recognition method based on probabilistic soft logic PSL of the present invention, image 3 It is a schematic flow chart of the second embodiment of the event recognition method based on probabilistic soft logic PSL of the present invention; as figure 1 and image 3 As shown, S2012-S2017 in Embodiment 2 of the event recognition method based on probabilistic soft logic PSL of the present invention is the same as S1011-1016 in Embodiment 1, and S202 is the same as S102. The difference is that S2011 is also included, that is, this S201 in Embodiment 2 of the event recognition method based on probabilistic soft logic PSL of the invention includes:

[0057] S2011. Obtain candidate high-dimensional category information; here, clustering technology is used to mine high-dimensional information on all thesaurus data sets, and subsequent feature extraction steps will use these high-dimensional information to construct fea...

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 present invention provides an event recognition method and system based on probabilistic soft logic PSL, the method includes: calculating the conditional probability of candidates and events, and two different candidates, two different events, event and theme, and candidate and theme occurrence Conditional probability in the same sentence and / or document; set corresponding variables for different conditional probabilities in the PSL model, design and iterate according to the variable formula of the PSL model, to maximize the variables corresponding to the conditional probability of the candidate and the event , get the specific event corresponding to the candidate under the maximization condition, and form an event recognition model. The method of the invention can improve the accuracy of event recognition.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, in particular to an event recognition method and system based on probabilistic soft logic PSL. Background technique [0002] With the vigorous development of the Internet and the increasing popularity of network communication terminals, people are exposed to massive amounts of information in various fields every day, such as news in military, sports, entertainment and other fields. How to find interesting events from these disordered, messy and unstructured mass information has become an urgent problem to be solved, and event identification (Event Identification) technology is a powerful means to solve this problem. Event recognition is an independent subtask of Event Extraction (Event Extraction), which mainly studies how to identify events and their types that users are interested in from unstructured text containing event information. [0003] Event recognition is a subtas...

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 & AuthorityPatents(China)
IPC IPC(8): G06F17/27G06K9/62
Inventor刘康赵军徐立恒刘树林
OwnerINST OF AUTOMATION CHINESE ACAD OF SCI