一种基于事实知识的实体相关度计算方法

摘要
参考文献
相关文章 (15)

全文: PDF (4420 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要在近来出现的面向实体的搜索服务中,准确地预测实体间的相关程度是至关重要的。该文提出了一种基于实体的事实知识,即利用 “实体—属性—属性值”(SPO)记录进行实体相关度计算的方法。该文通过基于属性和属性值的两步概率估计,将实体表示为一个属性值词的概率分布列,并通过比对两个实体共享的属性值词汇得出二者的相关度。实验表明,在用于面向实体搜索的相关实体排序问题上,该文方法达到了80.9%的平均top-5准确率,优于词袋方法和基于查询日志共现的方法。此外,该文通过定量分析,考察了不同领域的用户需求特性对实体相关度计算结果的影响。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孙叔琦
	孙珂
	赵世奇
	李生
	王海峰
	杨沐昀

关键词 ：实体相关度, 实体—属性—属性值(SPO)记录, 用户需求, 面向实体的搜索,

Abstract：In the emerging entity-oriented search service, an accurate prediction of the relatedness between entities is essential. This paper proposes an approach to compute entity relatedness based on entities' fact knowledge, i.e., subject-property-object (SPO) records. We adopt a two-step estimation based on property and object, mapping an entity to a discrete distribution of the object words, and obtained two entities' relatedness by comparing the object words they share. On the related entity re-ranking problem in entity-oriented search, experimental results showed that our approach achieves 80.9% top-5 precision on average, outperforming the bag-of-words and query log co-occurrence based approaches. We also conducted quantitative analysis to find out how user demand in different domains affects the relatedness computation.

收稿日期: 2014-07-28

中图分类号:

TP391

基金资助:国家自然科学基金项目(61272384,61370170,61105072)

作者简介: 孙叔琦（1985—），博士研究生，主要研究领域为信息抽取、文本挖掘。E-mail: sqsun@mtlab.hit.edu.cn
孙珂(1982—)，博士，主要研究领域为自然语言处理。E-mail: sunke@baidu.com
赵世奇（1981—），博士，主要研究领域为自然语言处理。E-mail: zhaoshiqi@baidu.com

链接本文:

http://jcip.cipsc.org.cn/CN/Y2016/V30/I3/178

[1] J Pound,P Mika,H Zaragoza. Ad-hoc object retrieval in the web of data［C］//Proceedings of the 19th International Conference on World Wide Web,WWW'10. New York,NY,USA: ACM. 2010: 771-780.
［2］M Strube,S P Ponzetto. Wikirelate! Computing semantic relatedness using Wikipedia［C］//Proceedings of the 21st National Conference on Artificial Intelligence-Volume 2,AAAI'06. AAAI Press,2006: 1419-1424.
［3］J Liu,L Birnbaum. Measuring semantic similarity between named entities by searching the web directory［C］//Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence,WI '07. Washington,DC,USA: IEEE Computer Society,2007: 461-465.
［4］S P Ponzetto,M Strube. Knowledge derived from Wikipedia for computing semantic relatedness［J］. J. Artif. Int. Res.,2007,30(1): 181-212.
［5］S Tuarob,P Mitra,C L Giles. Taxonomy-based query-dependent schemes for profile similarity measurement［C］//Proceedings of the 1st Joint International Workshop on Entity-Oriented and Semantic Search,JIWES '12. NewYork,NY,USA: ACM,2012,8:1-8,6.
［6］Y Ollivier,P Senellart. Finding related pages using green measures: an illustration with Wikipedia［C］//Proceedings of the 22nd National Conference on Artificial Intelligence-Volume 2,AAAI'07. AAAI Press,2007: 1427-1433.
［7］D Turdakov,P Velikhov. Semantic relatedness metric for Wikipedia concepts based on link analysis and its application to word sense disambiguation［C］//Proceedings of the SYRCoDIS,2008.
［8］Y Sun,J Han,X Yan,et al. Pathsim: Meta path-based top-k similarity search in heterogeneous information networks［J］. PVLDB,2011,4(11): 992-1003.
［9］X Yu,Y Sun,B Norick,et al. User guided entity similarity search using meta-path selection in heterogeneous information networks［C］//Proceedings of the 21st ACM International Conference on Information and Knowledge Management,CIKM'12. New York,NY,USA: ACM. 2012: 2025-2029.
［10］J Hoffart,S Seufert,D B Nguyen,et al. Kore: Key phrase overlap relatedness for entity disambiguation［C］//Proceedings of the 21st ACM International Conference on Information and Knowledge Management,CIKM '12. New York,NY,USA: ACM,2012: 545-554.
［11］D Milne,I H Witten. An effective,low-cost measure of semantic relatedness obtained from Wikipedia links［C］//Proceeding of AAAI Workshop on Wikipedia and Artificial Intelligence: an Evolving Synergy. AAAI Press,2008: 25-30.
［12］P Ogilvie,J Callan. Combining document representations for known-item search［C］//Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval,SIGIR '03. NewYork,NY,USA: ACM,2003: 143-150.
［13］P Ogilvie,J Callan. Hierarchical language models for XML component retrieval［C］//Proceedings of the 3rd International Conference on Initiative for the Evaluation of XML Retrieval,INEX'04. Berlin,Heidelberg: Springer-Verlag,2005: 224-237.
［14］J Kim,X Xue,W B Croft. A probabilistic retrieval model for semi-structured data［C］//Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval,ECIR '09. Berlin,Heidelberg: Springer-Verlag,2009: 228-239.
［15］R Neumayer,K Balog,K Norvag. On the modeling of entities for ad-hoc entity search in the web of data［C］//Proceedings of the 34th European conference on Advances in Information Retrieval,ECIR'12. Berlin,Heidelberg: Springer-Verlag,2012: 133-145.
[16］X Han,J Zhao. Structural semantic relatedness: a knowledge-based method to named entity disambiguation［C］//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics,ACL '10. Stroudsburg,PA,USA: Association for Computational Linguistics,2010: 50-59.
［17］Davis A Veloso,A S da Silva,W Meira,et al. Named entity disambiguation in streaming data［C］//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1,ACL '12. Stroudsburg,PA,USA: Association for Computational Linguistics,2012: 815-824.
［18］D Milne,I H Witten. Learning to link with Wikipedia［C］//Proceedings of the 17th ACM Conference on Information and Knowledge Management,CIKM'08. New York,NY,USA: ACM,2008: 509-518.