Supervised Local Contexts Aggregation for Effective Session Search

详细信息    查看全文

• 关键词：Session search ; Context ; Aggregation
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9626
• 期：1
• 页码：58-71
• 全文大小：540 KB
• 参考文献：1.Bendersky, M., Fisher, D., Croft, W.B.: Umass at trec 2010 web track: term dependence, spam filtering and quality bias. In: TREC (2010)
  2.Bennett, P.N., White, R.W., Chu, W., Dumais, S.T., Bailey, P., Borisyuk, F., Cui, X.: Modeling the impact of short- and long-term behavior on search personalization. In: SIGIR (2012)
  3.Cao, H., Jiang, D., Pei, J., Chen, E., Li, H.: Towards context-aware search by learning a very large variable length hidden markov model from search logs. In: WWW (2009)
  4.Collins-Thompson, K., Bennett, P.N., White, R.W., de la Chica, S., Sontag, D.: Personalizing web search results by reading level. In: CIKM (2011)
  5.Friedman, J.H.: Greedy function approximation: a gradient boosting machine. In: Annals of Statistics (2001)
  6.Guan, D., Zhang, S., Yang, H.: Utilizing query change for session search. In: SIGIR (2013)
  7.Guo, Q., White, R.W., Dumais, S.T., Wang, J., Anderson, B.: Predicting query performance using query, result, and user interaction features. In: RIAO (2010)
  8.Jiang, D., Leung, K.W.T., Ng, W.: Context-aware search personalization with concept preference. In: CIKM (2011)
  9.Jiang, J., He, D., Allan, J.: Searching, browsing, and clicking in a search session: changes in user behavior by task and over time. In: SIGIR (2014)
  10.Jiang, J., He, D., Han, S.: On duplicate results in a search session. In: TREC (2012)
  11.Joachims, T.: Training linear svms in linear time. In: KDD (2006)
  12.Kanoulas, E., Carterette, B., Hall, M., Clough, P., Sanderson, M.: Overview of the trec 2011 session track. In: TREC (2011)
  13.Kanoulas, E., Carterette, B., Hall, M., Clough, P., Sanderson, M.: Overview of the trec 2012 session track. In: TREC (2012)
  14.Kharitonov, E., Macdonald, C., Serdyukov, P., Ounis, I.: Intent models for contextualising and diversifying query suggestions. In: CIKM (2013)
  15.Lavrenko, V., Croft, W.B.: Relevance-based language models. In: SIGIR (2001)
  16.Li, X., Guo, C., Chu, W., Wang, Y.Y.: Deep learning powered in-session contextual ranking using clickthrough data. In: NIPS Workshop on Personalization: Methods and Applications (2014)
  17.Liu, C., Gwizdka, J., Liu, J.: Helping identify when users find useful documents: examination of query reformulation intervals. In: IIiX (2010)
  18.Liu, T., Zhang, C., Gao, Y., Xiao, W., Huang, H.: Bupt\(\_\) wildcat at trec 2011 session track. In: TREC (2011)
  19.Liu, T.Y.: Learning to Rank for Information Retrieval. Springer, Heidelberg (2011)CrossRef MATH
  20.Luo, J., Zhang, S., Dong, X., Yang, H.: Designing states, actions, and rewards for using POMDP in session search. In: Hanbury, A., Kazai, G., Rauber, A., Fuhr, N. (eds.) ECIR 2015. LNCS, vol. 9022, pp. 526–537. Springer, Heidelberg (2015)
  21.Manning, C.D., Raghavan, P., Schütze, H.: An Introduction to Information Retrieval. Springer, Heidelberg (2011)MATH
  22.Raman, K., Bennett, P.N., Collins-Thompson, K.: Toward whole-session relevance: exploring intrinsic diversity in web search. In: SIGIR (2013)
  23.Rendle, S., Gantner, Z., Freudenthaler, C., Schmidt-Thieme, L.: Fast context-aware recommendations with factorization machines. In: SIGIR (2011)
  24.Shen, X., Tan, B., Zhai, C.: Context-sensitive information retrieval using implicit feedback. In: SIGIR (2005)
  25.Shokouhi, M., White, R.W., Bennett, P., Radlinski, F.: Fighting search engine amnesia: reranking repeated results. In: SIGIR (2013)
  26.Ustinovskiy, Y., Serdyukov, P.: Personalization of web-search using short-term browsing context. In: CIKM (2013)
  27.Xiang, B., Jiang, D., Pei, J., Sun, X., Chen, E., Li, H.: Context-aware ranking in web search. In: SIGIR (2010)
  
• 作者单位：Zhiwei Zhang (21)
  Jingang Wang (22)
  Tao Wu (21)
  Pengjie Ren (23)
  Zhumin Chen (23)
  Luo Si (21)
  
  21. Department of Computer Science, Purdue University, West Lafayette, USA
  22. School of Computer Science, Beijing Institute of Technology, Beijing, China
  23. School of Computer Science and Technology, Shandong University, Jinan, China
  
• 丛书名：Advances in Information Retrieval
• ISBN：978-3-319-30671-1
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Existing research on web search has mainly focused on the optimization and evaluation of single queries. However, in some complex search tasks, users usually need to interact with the search engine multiple times before their needs can be satisfied, the process of which is known as session search. The key to this problem relies on how to utilize the session context from preceding interactions to improve the search accuracy for the current query. Unfortunately, existing research on this topic only formulated limited modeling for session contexts, which in fact can exhibit considerable variations. In this paper, we propose Supervised Local Context Aggregation (SLCA) as a principled framework for complex session context modeling. In SLCA, the global session context is formulated as the combination of local contexts between consecutive interactions. These local contexts are further weighted by multiple weighting hypotheses. Finally, a supervised ranking aggregation is adopted for effective optimization. Extensive experiments on TREC11/12 session track show that our proposed SLCA algorithm outperforms many other session search methods, and achieves the state-of-the-art results.