在计算广告学中,为用户查询返回相关的广告一直是研究的热点。然而用户的查询一般比较简短,广告的表示也局限在简短的创意和一些竞价词上,返回符合用户查询意图的广告十分困难。为了解决这个问题,该文提出利用多特征融合的方法进行广告查询扩展,先将查询输入到搜索引擎中,获得Top-k网页查询结果,将它们作为获取扩展词的外部资源,由于采用一般的特征选取方法获取扩展词采用的特征比较单一,缺乏语义信息,容易产生主题漂移现象,该文通过计算扩展词和查询词在网页查询结果中的共现度,并融合传统的TF特征和词性信息,获得与原始查询语义相关的扩展词。在真实的广告语料上的实验结果显示,基于多特征融合的选择广告扩展词的方法能有效地提高返回广告的相关性。
Abstract
In the computational advertising, how to return more relevant ad results for web query is a fundamental issue. Due to short web queries and the short ads which contains 15-20 bid phrases on average for each ad, it is very difficult to return the relevant ads meeting the need of users. In this paper, we propose a query expansion approach based on feature fusion to solve the problem. We use web search results initially returned for the query to create a pool of relevant documents. To avoid the topic drift of the normal query expansion algorithms based on simple feature and lack of semantic information, we compute the co-occurrence of expansion term and query term in the web search results with the traditional feature of TF and part-of-speech information. The result got on the authentic ads dataset shows that the query expansion approach based on multi-fusion can return more relevant ads.
Key wordssponsored search; query expansion; term co-occurrence
关键词
搜索广告 /
查询扩展 /
词共现
{{custom_keyword}} /
Key words
sponsored search /
query expansion /
term co-occurrence
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] A. Broder, M. Ciaramita, D. Metzler, et al. To swing or not to swing: learning when (not) to advertise[C]//Proceeding of the 17th ACM Conference on Information and Knowledge Management (CIKM 2008), Napa Valley, California, 2008: 1003-1012.
[2] H. Wang, Y. Liang, L. Fu, et al. Efficient query expansion for advertisement search[C]//Proceedings of the 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR2009), Boston, 2009: 51-58.
[3] R. Jones, B. Rey, O. Madani, et al. Generating query substitutions[C]//Proceedings of the 15th International Conference on World Wide Web (WWW2006), New York, 2006: 387-396.
[4] A. Z. Broder, P. Ciccolo, M. Fontoura, et al. Search advertising using web relevance feedback[C]//Proceeding of the 17th ACM Conference on Information and Knowledge Management (CIKM2008), Napa Valley, California, 2008: 1013-1022.
[5] A. Broder, P. Ciccolo, E. Gabrilovich, et al. Online expansion of rare queries for sponsored search[C]//Proceedings of the 18th International Conference on World Wide Web (WWW2009), Madrid, 2009: 511-520.
[6] C. Danescu, A. Broder, E. Gabrilobich, et al. Competing for users attention: on the interplay between organic and sponsored search results[C]//Proceedings of the 19th International Conference on World Wide Web (WWW2010), New York, 2010: 291-300.
[7] H. Raghavan, R. Iyer. Evaluating vector-space and probabilistic models for query to ad matching[C]//SIGIR08 Workshop on Information Retrieval in Advertising (IRA), 2008.
[8] J. Xu, B. Croft. Query expansion using local and global document analysic[C]//Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR1996), Zurich, Switzerland, 1996: 4-11.
[9] G. Cao, J. Nie, J. Cao, et al. Selecting good expansion terms for pseudo-relevance feedback[C]//Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR2008), Singapore, 2008: 243-250.
[10] 丁国栋,白硕,王斌. 一种基于局部共现的查询扩展方法[J]. 中文信息学报,2006,20(3): 84-91.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金资助项目(60673039,60973068);国家863高科技计划资助项目(2006AA01Z151);教育部留学回国人员科研启动基金和高等学校博士学科点专项科研基金资助(20090041110002)
{{custom_fund}}
PDF(1170 KB)
