Event Recognition Based on Deep Belief Network

ZHANG Ya-jun; LIU Zong-tian; ZHOU Wen

doi:10.3969/j.issn.0372-2112.2017.06.020

您当前的位置：

首页 >

文章列表页 >

Event Recognition Based on Deep Belief Network

更新时间：2025-07-16

- Event Recognition Based on Deep Belief Network
- Acta Electronica Sinica Vol. 45, Issue 6, Pages: 1415-1423(2017)
- 作者机构：
  
  上海大学计算机工程与科学学院,上海,200444
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61273328, No.61305053, No.71203135)
- DOI：10.3969/j.issn.0372-2112.2017.06.020
  CLC： TP391
- Published：2017
- 稿件说明：
移动端阅览
ZHANG Ya-jun, LIU Zong-tian, ZHOU Wen. Event Recognition Based on Deep Belief Network[J]. Acta Electronica Sinica, 2017, 45(6): 1415-1423.
DOI：

ZHANG Ya-jun, LIU Zong-tian, ZHOU Wen. Event Recognition Based on Deep Belief Network[J]. Acta Electronica Sinica, 2017, 45(6): 1415-1423. DOI： 10.3969/j.issn.0372-2112.2017.06.020.

摘要

事件识别是信息抽取的重要基础.为了克服现有事件识别方法的缺陷，本文提出一种基于深度学习的事件识别模型.首先，我们通过分词系统获得候选词并将它们分为五种类型.然后选择六种识别特征并制定相应的特征表示规则用来将词转化为向量样例.最后我们通过深度信念网络抽取词的深层语义信息，并由Back-Propagation（BP）神经网络识别事件.实验显示模型最高

值达85.17%.同时，本文还提出了一种融合无监督和有监督两种学习方式的混合监督深度信念网络，该网络能够提高识别效果（

值达89.2%）并控制训练时间（增加27.50%）.

Abstract

Event recognition is critical to information extraction.To overcome limitations of the exiting event recognition approaches

we proposed an event recognition model based on deep learning (DL-ERM).Firstly

we acquired candidate words through a word segmentation system and classified them into five categories.Then

we selected six recognition feature layers and constructed corresponding feature representation rules to convert words into vector samples.Finally

we employed a deep belief network (DBN) to extract deep semantic features of words

and used a back propagation neural network to identify events.The results of experiments show that the maximum

-measure is 85.17%.Furthermore

we presented a hybrid-supervised DBN

which combines the unsupervised and supervi

sed learning.The novel DBN improves the recognition performance (89.2%

-measure) and effectively controls the training time (increased by 27.50%).

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Differentially Private with Sparse and Smooth Self-Distillation

Operator Fusion Method and Hardware Architecture Design Based on Non-Standard Operators

A Method for Enhancing the Quality of Decompressed Point Clouds Based on Attention-Fused Multi-Scale Features

Research on Joint Source-Channel Coding Method Based on Deep Compressive Sensing

Related Author

HUANG Yu-zhe

GUAN Yong-yuan

WEI Song-jie

ZHAO Deng-feng

XUE Da-xuan

ZHAO Su-yun

CHEN Hong

WANG Ying

Related Institution

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

School of Information, Renmin University of China

College of Information Engineering, Capital Normal University

School of Mathematical Science, Capital Normal University

Faculty of Software Technologics, Shanxi Agricultural University

⁰