Entity Relation Extraction Based on Improved Attention Mechanism

FENG Jian-zhou; SONG Sha-sha; WANG Yuan-zhuo; LIU Ya-kun; WU Hong-ying; GONG Hao

doi:10.3969/j.issn.0372-2112.2019.08.012

您当前的位置：

首页 >

文章列表页 >

Entity Relation Extraction Based on Improved Attention Mechanism

更新时间：2025-07-16

- Entity Relation Extraction Based on Improved Attention Mechanism
- Acta Electronica Sinica Vol. 47, Issue 8, Pages: 1692-1700(2019)
- 作者机构：
  
  1. 燕山大学信息科学与工程学院,河北,秦皇岛,066000
  2. 中国科学院计算技术研究所,北京,100080
  3. 燕山大学信息科学与工程学院,河北,秦皇岛,066000
  4. 中国科学院计算技术研究所,北京,100080
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2019.08.012
  CLC： TP311
- Published Online：25 August 2019，
  
  Published：2019
- 稿件说明：
移动端阅览
FENG Jian-zhou, SONG Sha-sha, WANG Yuan-zhuo, et al. Entity Relation Extraction Based on Improved Attention Mechanism[J]. Acta Electronica Sinica, 2019, 47(8): 1692-1700.
DOI：

FENG Jian-zhou, SONG Sha-sha, WANG Yuan-zhuo, et al. Entity Relation Extraction Based on Improved Attention Mechanism[J]. Acta Electronica Sinica, 2019, 47(8): 1692-1700. DOI： 10.3969/j.issn.0372-2112.2019.08.012.

摘要

实体关系抽取是知识库构建中至关重要的一个环节.在众多的实体关系抽取方法中，远程监督结合神经网络模型的方法在准确率等性能上是比较令人满意的，但远程监督获取的标注语料中往往存在大量的噪声数据，给实体关系抽取模型的训练带来了很大的影响.本文提出一种基于改进注意力机制的卷积神经网络实体关系抽取模型.该模型针对包含同一实体对的句子集合，从中尽可能地找出所有体现该实体对关系的正实例，构建组合句子向量，抛弃可能的噪声句子，从而最大程度地降低噪声句子的影响又能充分利用正实例的语义信息.实验证明，本文提出的关系抽取模型在准确率上优于对比的关系抽取模型.

Abstract

Entity relation extraction is a crucial part of knowledge base construction. Among many methods of relationship extraction

the method of distant supervision combined with neural network model is satisfactory in terms of accuracy and other performance. However

there is often a large amount of noise data in the labeled corpus obtained by distant supervision

which has a great impact on the training of relationship extraction model. In this paper

we propose an entity relationship extraction model of convolutional neural network based on improved attention mechanism. Aiming at the sentence set containing the same entity pair

this model tries to find out all the positive instances that embody the relationship between the entity pair

construct the combined sentence vector

and discard the possible noise sentences

so as to minimize the impact of noise sentences and make full use of the semantic information of positive instances. Experimental results show that the accuracy of the proposed relation extraction model is better than that of the comparative relation extraction model.

关键词

Keywords

references

Views

224

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Quantification Method of Convolutional Neural Network Based on Data Standard Deviation

Clinical Relation Extraction via Dual Piecewise Attention Neural Tensor Network

HAN: Hotspot-Aware Attention Enhanced News Recommendation

Feature-Space Optimization-Inspired and Self-Attention Enhanced Neural Network Reconstruction Algorithm for Image Compressive Sensing

Single Image Super-Resolution Reconstruction Using Deep Residual Networks with Non-decimated Wavelet Edge Learning

Related Author

YANG Guang

HUANG Yun

ZHANG Fan

GUO Wei

CHEN Li

WEI Hao

TANG Huan-ling

ZHOU Ai

Related Institution

Henan Administration of Radio and Television Monitoring Center，， Hennan

National Digital Switching System Engineering Technology Research Center，， Hennan

Information Engineering University，， Hennan

School of Software， Dalian University of Foreign Languages

Information Science and Technology College， Dalian Maritime University

⁰