信息检索的效果很大程度上取决于用户能否输入恰当的查询来描述自身信息需求。很多查询通常简短而模糊,甚至包含噪音。查询推荐技术可以帮助用户提炼查询、准确描述信息需求。为了获得高质量的查询推荐,在大规模“查询-链接”二部图上采用随机漫步方法产生候选集合。利用摘要点击信息对候选列表进行重排序,使得体现用户意图的查询排在比较高的位置。最终采用基于学习的算法对推荐查询中可能存在的噪声进行过滤。基于真实用户行为数据的实验表明该方法取得了较好的效果。
Abstract
The effectiveness of information retrieval from the web largely depends on whether users can properly describe their information needs in the queries issue to the search engines. However, many search queries are short, ambiguous or even noisy. Query recommendation technology help users refine their queries and describe the information needs clearly. In order to obtain high quality query recommendations, query candidates are at first generated with a random walk strategy adopted on Query-URL bipartite graph. Snippet click behavior information is then adopted to re-rank the candidate lists infavor of the queries representing user intents. Learning based algorithms are finally utilized to reduce the possible noises in recommendations. Experiment on practical search user behavior data shows the effectiveness of the proposed method.
关键词
查询推荐 /
用户意图挖掘 /
摘要点击模型
{{custom_keyword}} /
Key words
query recommendation /
user intent mining /
snippet click graph
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 维基百科.Web search engine[EB/OL]. [2012年6月5日]. http://en.wikipedia.org/wiki/Web_search_engine.
[2] 余慧佳, 刘奕群, 张敏, 等. 基于大规模日志分析的网络搜索引擎用户行为研究[C].第三届学生计算语言学研讨会, 中国辽宁沈阳, 2006.
[3] Liu Y, Miao J, Zhang M, et al. How do users describe their information need: Query recommendation based on snippet click model. Expert Systems with Applications, 2011,38(11):13847-13856.
[4] Boldi P, Bonchi F, Castillo C, et al. The query-flow graph: model and applications[C]//Proceedings of CIKM 08, New York, NY, USA, 2008.
[5] Craswell N, Szummer M. Random walks on the click graph[C]//Proceedings of SIGIR 07, New York, NY, USA, 2007.
[6] Zhang Z, Nasraoui O. Mining search engine query logs for social filtering-based query recommendation[J]. Applied Soft Computing, 2008,8(4):1326-1334.
[7] Mei Q, Zhou D, Church K. Query suggestion using hitting time[C]//Proceedings of CIKM 08, New York, NY, USA, 2008.
[8] Song Y, Zhou D, He L. Query suggestion by constructing term-transition graphs[C]//Proceedings of WSDM 12, New York, NY, USA, 2012.
[9] Cao H, Jiang D, Pei J, et al. Context-aware query suggestion by mining click-through and session data[C]//Proceedings of KDD 08, New York, NY, USA, 2008.
[10] Sadikov E, Madhavan J, Wang L, et al. Clustering query refinements by user intent[C]//Proceedings of the 19th international conference on World wide web. ACM, 2010: 841-850.
[11] Broder A. A taxonomy of web search[C], 2002.
[12] Boser B E, Guyon I M, Vapnik V N. A training algorithm for optimal margin classifiers[C]//Proceedings of COLT 92, New York, NY, USA, 1992.
[13] Rvelin K J A, Kek A L A, Inen J. Cumulated gain-based evaluation of IR techniques[J]. ACM Transactions on Information Systems (TOIS), 2002,20(4):422-446.
[14] Jones K S, van Rijsbergen C J. Information retrieval test collections[J]. Journal of documentation, 1976,32(1):59-75.
[15] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011,2(3):27.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家863高科技项目(2011AA01A205);自然科学基金(60903107, 61073071)
{{custom_fund}}
PDF(2993 KB)
