空间分析等方法 [1][2][3][6][7] 。
A place graph is an abstract representation of human place knowledge, which models spatial references. A place graph can be used for various tasks that rely on reasoning and querying of the stored knowledge. In related work, place graphs were constructed from parsing natural language place descriptions using language processing techniques. In this research, we present an innovative approach to derive place graphs from information stored in spatial databases, with a demonstration using OpenStreetMap data. The approach provides a complementary way to generating place graphs from natural language descriptions.
首先基于用户偏好一致性假设,根据信息函数对所有提及进行排序,得到歧义最小的提及,利用消歧算法消歧,并将返回的确认实体纳入消歧函数.通过这种迭代策略让正确的结果正向传递给下一层更模糊的消歧任务.在人工标注测试集上的实验结果表明,本文方法具有良好的性能.
Yuheng Li (李禹恒)合作论文数1
Martin Tomko合作论文数Department of Infrastructure Engineering, School of Electrical, Mechanical and Infrastructure Engineering, Faculty of Engineering and Information Technology, The University of Melbourne1
Yirong Wu (吴一戎)合作论文数Aerospace Information Research Institute, Chinese Academy of Sciences;Institute of Electronics, Chinese Academy of Sciences;School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences1
Yu Huang (黄宇)合作论文数中国科学院上海药物研究所1
Feng Zhen (甄峰)合作论文数Department of Urban Planning and Design, School of Architecture and Urban Planning, Nanjing University1
Kun Fu (付琨)合作论文数Aerospace Information Research Institute, Chinese Academy of Sciences;University of Chinese Academy of Sciences1
Xiao Qin (秦萧)合作论文数Key Laboratory of Urban AI and Green Built Environment of Provincial Higher Education Institutes, School of Architecture and Urban Planning, Nanjing University1
Ehsan Hamzei合作论文数University of Melbourne1
Maria Vasardani合作论文数Department of Infrastructure Engineering, University of Melbourne1
Stephan Winter合作论文数Department of Infrastructure Engineering, The University of Melbourne1
