自然语言空间查询中应用编辑距离的规则匹配模型  

Research on Rule Matching in Natural Language Spatial Query Based on Levenshtein Distance

作　　者：盖森[1] 刘建忠[1] 熊伟[1] 张心悦[1] 李江鹏 

机构地区：[1]信息工程大学 [2]61206部队

出　　处：《测绘科学技术学报》2015年第4期416-421,共6页Journal of Geomatics Science and Technology

基　　金：国家自然科学基金项目(41471337)

摘　　要：自然语言空间查询是智能信息检索在GIS领域的扩展。自然语言的自由灵活性在降低用户查询难度的同时,也对查询语句的规则匹配增加了难度。鉴于此,提出基于编辑距离的规则匹配模型。在词语层面,计算编辑相似度和语义相似度提供候选项,通过用户选择来建立未登录词与空间词库的匹配关系;在语句层面,应用编辑距离的思想来实现未登录句式的规则匹配。最后,开发了规则匹配工具,通过实验验证了模型的可行性。Natural language spatial query is the expansion of intelligent information retrieval in GIS. The flexibility of natural language reduces the query difficulty for users, and meanwhile increases the rule matehing difficulty of query sentences. Owing to this, a rule matching model was put forward based on levenshtein distance. In the word level, candidate words were provided through edit similarity and semantic similarity, which could establish the re- lation between unknown words and spatial thesaurus. In the sentence level, the idea of levenshtein distance was used to realize the rule matching of unknown sentence structure. Finally, a rule matching tool is developed, which verifies the feasibility of the model.

关 键 词：编辑距离 规则匹配 自然语言 空间查询 信息检索 

分 类 号：P208[天文地球—地图制图学与地理信息工程]