人工智能培训

搜索

人工智能论文:基于实体链接的抗感染药物本体半自动构建方法(Approach for Semi-automatic Construction of Anti-in

[复制链接]
xc133280 发表于 2018-12-6 11:59:56 | 显示全部楼层 |阅读模式
xc133280 2018-12-6 11:59:56 131 0 显示全部楼层
人工智能论文:基于实体链接的抗感染药物本体半自动构建方法(Approach for Semi-automatic Construction of Anti-infective Drug Ontology  Based on Entity Linking)本体可以用于解释自然语言。为了构建抗感染药物本体,需要设计和部署一个方法步骤来进行实体发现和连接。医学同义词资源一直是医学自然语言处理(NLP)的重要组成部分。但是,存在诸如低精度和低回忆率的问题。在本研究中,采用NLP方法生成候选实体。分析开放本体以提取语义关系。选择六个字向量特征和字级特征来执行实体链接。研究了具有单一特征和不同特征组合的同义词的提取结果。实验表明,我们选择的特征准确率达到86.77%,召回率为89.03%,F1得分为87.89%。本文最后介绍了所提出的本体的结构及其相关的统计数据。
Ontology can be used for the interpretation of natural language.To constructan anti-infective drug ontology, one needs to design and deploy amethodological step to carry out the entity discovery and linking.Medicalsynonym resources have been an important part of medical natural languageprocessing (NLP).However, there are problems such as low precision and lowrecall rate.In this study, an NLP approach is adopted to generate candidateentities.Open ontology is analyzed to extract semantic relations.Six-wordvector features and word-level features are selected to perform the entitylinking.The extraction results of synonyms with a single feature and differentcombinations of features are studied.Experiments show that our selectedfeatures have achieved a precision rate of 86.77%, a recall rate of 89.03% andan F1 score of 87.89%.This paper finally presents the structure of theproposed ontology and its relevant statistical data.人工智能论文:基于实体链接的抗感染药物本体半自动构建方法(Approach for Semi-automatic Construction of Anti-infective Drug Ontology  Based on Entity Linking) mn1bBp51n8W4B885.jpg
URL地址:https://arxiv.org/abs/1812.01887     ----pdf下载地址:https://arxiv.org/pdf/1812.01887    ----人工智能论文:基于实体链接的抗感染药物本体半自动构建方法(Approach for Semi-automatic Construction of Anti-infective Drug Ontology  Based on Entity Linking)
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

xc133280当前离线
新手上路

查看:131 | 回复:0

快速回复 返回顶部 返回列表