| 摘要: |
| 随着语义Web 的快速发展,语义Web 数据大幅增长.在语义Web 中,单个对象很可能由多个不同的标识符(例如URI)指称.语义Web 中,对象共指的消解是识别语义Web 中指称相同对象的不同标识符,并消除描述这些标识符的RDF(resource description framework)数据之间不一致性的过程,它对于语义Web 数据的融合、搜索、浏览等具有重要作用.首先,形式化定义了语义Web 中对象共指的消解问题;然后,从对象共指识别使用的特征、数据冲突的消解方式、对象共指消解方法的适用范围、现有原型系统和基准测试集这5 个方面调研了最新的研究进展;最后,讨论了尚存的挑战,并展望未来可能的研究发展方向. |
| 关键词: 对象共指 共指消解 实例匹配 语义Web 数据融合 |
| DOI：10.3724/SP.J.1001.2012.04215 |
| 分类号: |
| 基金项目:国家自然科学基金(61003018, 61100040, 61021062); 国家社会科学基金(11AZD121); 国家教育部博士点基金(20100091120041); 江苏省自然科学基金(BK2011189) |
|
| Research on Resolving Object Coreference on the Semantic Web |
|
HU Wei1,2, BAI Wen-Yang1,2, QU Yu-Zhong1,2
|
|
1.State Key Laboratory for Novel Software Technology (Nanjing University), Nanjing 210093, China;2.Department of Computer Science and Technology, Nanjing University, Nanjing 210093, China
|
| Abstract: |
| Semantic Web data proliferates with the rapid growth of the semantic Web. An object on the semantic Web is likely to be denoted with many identifiers (e.g., URIs) by different parties. Resolving an object coreference on the semantic Web is to identify different identifiers for the same object and eliminate the inconsistency between their involved RDF (resource description framework) data, which is important for semantic Web data fusion, search, browsing, etc. In this paper, the problem of resolving object coreference on the semantic Web is first formalized. Next, the state of the art of works are surveyed and categorized into five aspects: The used characteristics for coreference identification, the mechanisms for data conflict resolution, the applicable scopes of current approaches, prototypes, and benchmarks. Finally, open research issues are discussed and possible future research directions are also pointed out. |
| Key words: object coreference coreference resolution instance matching semantic Web data fusion |
