检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:陈新元 陈庆强 谢晟祎[3] 陈但淡 CHEN Xin-yuan;CHEN Qing-qiang;XIE Sheng-yi;CHEN Dan-dan(College of Engineering and Technology,Fuzhou Technology and Business University,Fuzhou 350715,China;Information Science and Engineering College,Fujian University of Technology,Fuzhou 350118,China;Division of Teaching and Academic Affairs,Fujian Vocational College of Agriculture,Fuzhou 350181,China;Faculty of Teaching Affairs,Fuzhou Melbourne Polytechnic,Fuzhou 350121,China)
机构地区:[1]福州工商学院工学院,福建福州350715 [2]福建工程学院信息科学与工程学院,福建福州350118 [3]福建农业职业技术学院教学科研处,福建福州350181 [4]福州墨尔本理工职业学院教务处,福建福州350121
出 处:《唐山师范学院学报》2022年第3期66-71,共6页Journal of Tangshan Normal University
基 金:福建省中青年教师教育科研项目(JAT210619)。
摘 要:为提高问答系统准确率,引入知识图谱构建框架,借助元图结构描述知识,利用知识推理技术实现持续更新。问答系统集成传统Q&A问答模块和知识图推理模块,并行处理问题并传递给答案生成模块。进一步提取、优化主题、关键字和摘要以提高问答键值对匹配的准确率,并将情境信息以属性/标签的方式与问答键值对集成以缩小候选集。在教学实践中评估、验证系统功能/性能。To improve the question answering accuracy of Q&A systems,a framework for knowledge graph construction is proposed,in which meta-graph structure is employed to describe knowledge,reasoning techniques adopted to deliver continual knowledge updating.A traditional Q&A module and a knowledge graph reasoning module are integrated into the framework to complete the question answering process in parallel,another module called answer generation responsible for making the selection.Topics,keywords and abstracts are further optimized/extracted for better key-value matching while contextual information is attached to key-value pairs of questions and answers in the form of attributes/labels to narrow the candidate set.System function/performance is assessed and verified in teaching practice.
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38