查询结果:   翟社平,段宏宇,李兆兆.基于BILSTM_CRF的知识图谱实体抽取方法[J].计算机应用与软件,2019,36(5):269 - 274,280.
中文标题
基于BILSTM_CRF的知识图谱实体抽取方法
发表栏目
算法
摘要点击数
613
英文标题
KNOWLEDGE GRAPH ENTITY EXTRACTION BASED ON BILSTM_CRF
作 者
翟社平 段宏宇 李兆兆 Zhai Sheping Duan Hongyu Li Zhaozhao
作者单位
西安邮电大学计算机学院 陕西 西安 710121 陕西省网络数据分析与智能处理重点实验室 陕西 西安 710121    
英文单位
School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, Shaanxi, China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi’an 710121, Shaanxi, China    
关键词
知识图谱 实体抽取 神经网络 词向量 BILSTM_CRF模型
Keywords
Knowledge graph Entity extraction Neural network Word embedding BILSTM_CRF model
基金项目
工业和信息化部通信软科学项目(2018-R-26);陕西省自然科学基金资助项目(2012JM8044);陕西省社会科学基金资助项目(2016N008);陕西省教育厅科学研究计划资助项目(12JK0733);西安邮电大学研究生创新基金项目(CXL2016-13)
作者资料
翟社平,副教授,主研领域:语义网,知识图谱。段宏宇,硕士生。李兆兆,硕士生。 。
文章摘要
针对传统知识图谱实体抽取方法需要大量人工特征和专家知识的问题,提出一种基于BILSTM_CRF模型的神经网络结构实体抽取方法。它既能使用双向长短时记忆网络BILSTM(Bidirectional Long Short-Term Memory)提取文本信息的特征,又可利用条件随机场CRF(Conditional Random Fields)衡量序列标注的联系。该方法对输入的文本进行建模,把句子中的每个词转换为词向量;利用BILSTM处理分布式向量得到句子特征;使用CRF标注并抽取实体,得到最终结果。实验结果表明,该方法的准确率和召回率更高,F1值提升约8%,具有更强的适用性。
Abstract
In order to solve the problem that traditional knowledge atlas entity extraction method needed a lot of artificial features and expert knowledge, we proposed a neural network entity extraction method based on BILSTM_CRF model. It could use bidirectional long short-term memory(BILSTM) to extract the features of text information, and use conditional random fields(CRF) to measure the association of sequence labeling. In this method, the input text was modeled, and every word in the sentence was transformed into a word embedding. The distributed vectors were processed by BILSTM to get sentence features. And the CRF tagging and entity extraction were used to get the final results. The experimental results show that the proposed method has higher accuracy and recall rate, and the value of F1 is increased by about 8%, which has better applicability.
下载PDF全文