Short Bio

Zhicheng Dou is currently a professor at Renmin University of China and vice dean for Gaoling School of Artificial Intelligence. He received his Ph.D. and B.S. degrees in computer science and technology from the Nankai University in 2008 and 2003, respectively. He worked at Microsoft Research Asia from July 2008 to September 2014. His current research interests are Information Retrieval, Natural Language Processing , and Big Data Analysis. He received the Best Paper Runner-Up Award from SIGIR 2013, and the Best Paper Award from AIRS 2012. He served as the program co-chair of the short paper track for SIGIR 2019. Zhicheng Dou is not a pure research guy - besides writing papers, he also enjoys writing codes to convert cool ideas into real systems.

Contacts:

Academic Homepages

Publications

*: Corresponding author; ____ indicates the author is/was my student;
2021
  • Jing Yao, Zhicheng Dou*, Jian-Yun Nie, and Ji-Rong Wen. Looking Back on the Past: Active Learning with Historical Evaluation Results. in IEEE Transactions on Knowledge and Data Engineering. (TKDE 2021) (CCF A) (Download | DOI)
  • Jing Yao, Zhicheng Dou*, Jun Xu, and Ji-Rong Wen. RLPS: A Reinforcement Learning based Framework for Personalized Search. in Transactions on Information Systems (TOIS 2021) (CCF A) (Download | DOI)
  • Jing Yao, Zhicheng Dou*, and Ji-Rong Wen. FedPS: A Privacy Protection Enhanced Personalized Search Framework. Proceedings of 30th The Web Conference (WWW 2021) (CCF A) (Download)
  • Yutao Zhu, Kun Zhou, Jian-Yun Nie, Shengchao Liu, and Zhicheng Dou. Neural Sentence Ordering Based on Constraint Graphs. Proceedings of The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021) (CCF A) (Download)
  • Yutao Zhu, Jian-Yun Nie, Kun Zhou, Pan Du, and Zhicheng Dou. Content Selection Network for Document-grounded Retrieval-based Chatbots. Proceedings of the 43rd edition of the annual BCS-IRSG European Conference on Information Retrieval (ECIR 2021) (Download)
  • Zhumin Chen, Xueqi Cheng, Shoubin Dong, Zhicheng Dou, Jiafeng Guo, Xuanjing Huang, Yanyan Lan, Chenliang Li, Ru Li, Tie-Yan Liu, Yiqun Liu, Jun Ma, Bing Qin, Mingwen Wang, Ji-Rong Wen, Jun Xu, Min Zhang, Peng Zhang, Qi Zhang: Information retrieval: a view from the Chinese IR community. Frontiers Comput. Sci. 15(1): 151601 (2021) (Download | DOI)
2020
  • Zhengyi Ma, Zhicheng Dou*, Guanyue Bian, and Ji-Rong Wen. PSTIE: Time Information Enhanced Personalized Search. Proceedings of 29th ACM International Conference on Information and Knowledge Management (CIKM 2020) (CCF B) (Download | DOI)
  • Xubo Qin, Zhicheng Dou* and Ji-Rong Wen. Diversifying Search Results using Self-Attention Network. Proceedings of 29th ACM International Conference on Information and Knowledge Management (CIKM 2020) (CCF B) (Download | DOI)
  • Jing Yao, Zhicheng Dou* and Ji-Rong Wen. Employing Personal Word Embeddings for Personalized Search. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020) (CCF A) (Download | DOI)
  • Yujia Zhou, Zhicheng Dou* and Ji-Rong Wen. Encoding History with Context-aware Representation Learning for Personalized Search. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020) (CCF A) (Download | DOI)
  • Jiongnan Liu, Zhicheng Dou*, Xiaojie Wang, Shuqi Lu and Ji-Rong Wen. DVGAN: A Minimax Game for Search Result Diversification Combining Explicit and Implicit Features. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020) (CCF A) (Download | DOI)
  • Shuqi Lu, Zhicheng Dou*, Chenyan Xiong, Xiaojie Wang and Ji-Rong Wen. Knowledge Enhanced Personalized Search. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020) (CCF A) (Download | DOI)
  • Jing Yao, Zhicheng Dou*, Jun Xu, and Ji-Rong Wen. RLPer: A Reinforcement Learning Model for Personalized Search. Proceedings of The Web Conference 2020, April 20--24, 2020, Taipei, Taiwan (WWW 2020) (CCF A) (Download | DOI)
  • Anwen Hu, Zhicheng Dou*, Jian-Yun Nie, and Ji-Rong Wen. Leveraging Multi-token Entities in Document-level Named Entity Recognition. Proceedings of the thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020) (CCF A) (Download | DOI)
  • Yujia Zhou, Zhicheng Dou*, and Ji-Rong Wen. 2020. Enhancing Re-finding Behavior with External Memories for Personalized Search. In Proceedings of the 21th ACM International Conference on Web Search and Data Mining (WSDM '20). ACM, New York, NY, USA, (WSDM 2020) (CCF B) (Download | DOI)
  • Yutao Zhu, Ruihua Song, Zhicheng Dou*, Jian-Yun Nie, and Jin Zhou. ScriptWriter: Narrative-Guided Script Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, {ACL} 2020, Online, July 5-10, 2020: 8647-8657 (ACL 2020) (CCF A) (Download | DOI)
2019
  • Shuqi Lu, Zhicheng Dou*, Xu Jun, Jian-Yun Nie, and Ji-Rong Wen. PSGAN: A Minimax Game for Personalized Search with Limited and Noisy Click Data. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval: 555-564 (SIGIR 2019) (CCF A) (Download | DOI)
  • Zhicheng Dou*, Xue Yang, Diya Li, Ji-Rong Wen, and Tetsuya Sakai. Low-cost, bottom-up measures for evaluating search result diversification. Information Retrieval Journal (2019). (IRJ) (Download | DOI)
  • Yutao Zhu, Zhicheng Dou*, Jian-Yun Nie, and Ji-Rong Wen. ReBoost: A Retrieval-Boosted Sequence-to-Sequence Model for Neural Response Generation. Information Retrieval Journal (2019). (IRJ) (Download | DOI)
  • Juan Li, Zhicheng Dou*, Yutao Zhu, Xiaochen Zuo, and Ji-Rong Wen. Deep Cross-platform Product Matching in E-commerce. Information Retrieval Journal (2019). (IRJ) (Download | DOI)
  • Yujia Zhou, , Zhicheng Dou*, Songwei Ge, and Ji-Rong Wen. Dynamic Personalized Search Based on RNN with Attention Mechanism. Chinese Journal of Computer (2019), Vol 42. (Download | DOI)
  • Zhicheng Dou*, Xubo Qin, and Ji-Rong Wen. A Survey on Search Result Diversification. Chinese Journal of Computer (2019), Vol 42. (Download | DOI)
  • Shuqi Lu, Zhicheng Dou*, and Ji-Rong Wen. Research On Structural Data Extraction in Surgical Cases. Chinese Journal of Computer (2019), Vol 42. (Download | DOI)
  • Xiaochen Zuo, Zhicheng Dou*, Zhen Huang, Shuqi Lu. Product Category Mining Associated with Weibo Hot Topics. Journal of Computer Research and Development,2019, 56(09):1927-1938. (Download | DOI)
  • Anwen Hu, Zhicheng Dou*, and Ji-Rong Wen. Document-Level Named Entity Recognition by Incorporating Global and Neighbor Features. Information Retrieval. 25th China Conference, CCIR 2019, Fuzhou, China, September 20–22, 2019, Proceedings. (Download | DOI)
2018
  • Zhengbao Jiang, Zhicheng Dou*, Wayne Xin Zhao, Jian-Yun Nie, Ming Yue, and Ji-Rong Wen. Supervised Search Result Diversification via Subtopic Attention. IEEE Trans. Knowl. Data Eng. 30(10): 1971-1984 (2018) (TKDE) (CCF A) (Download | DOI)
  • Xiao-Jie Wang, Ji-Rong Wen, Zhicheng Dou*, Tetsuya Sakai, and Rui Zhang. Search Result Diversity Evaluation Based on Intent Hierarchies, IEEE Trans. Knowl. Data Eng. 30(1): 156-169 (2018) (TKDE) (CCF A) (Download | DOI)
  • Songwei Ge, Zhicheng Dou*, Zhengbao Jiang, Jian-Yun Nie, Ji-Rong Wen. Personalizing Search Results Using Hierarchical RNN with Query-aware Attention. in Proceedings of the 27th ACM International Conference on Information and Knowledge Management: 347-356 (CIKM 2018) (CCF B) (Download | DOI)
  • Ji-Rong Wen, Zhicheng Dou*, Ruihua Song: Personalized Web Search. Encyclopedia of Database Systems (2nd ed.) 2018
2017
  • Zhengbao Jiang, Ji-Rong Wen, Zhicheng Dou*, Wayne Xin Zhao, Jian-Yun Nie, Ming Yue. Learning to Diversify Search Results via Subtopic Attention. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2017) (CCF A) (Download | DOI)
  • Zhengbao Jiang, Zhicheng Dou*, Ji-Rong Wen. Generating Query Facets Using Knowledge Bases. IEEE Trans. Knowl. Data Eng. 29(2): 315-329 (2017) (TKDE) (CCF A) (Download | DOI)
  • Zhicheng Dou, Zhengbao Jiang, Jinxiu Li, Yichun Zhang, and Ji-Rong Wen. A Method of Mining Query Facets Based on Term Graph Analysis. Chinese Journal of Computer, 2017, 40(3):556-569. ((In Chinese) Download | DOI)
2016
  • Xiaojie Wang, Zhicheng Dou*, Tetsuya Sakai, and Ji-Rong Wen. Evaluating Search Result Diversity using Intent Hierarchies. In Proceedings of SIGIR, 2016. (SIGIR 2016) (CCF A) (Download | DOI)
  • Zhicheng Dou*, Zhengbao Jiang, Sha Hu, Ji-Rong Wen, Ruihua Song: Automatically Mining Facets for Queries from Their Search Results. IEEE Trans. Knowl. Data Eng. (TKDE) 28(2):385-397 (2016) (TKDE) (CCF A) (Download | DOI)
  • Sha Hu, Ji-Rong Wen, Zhicheng Dou, Shuo Shang. Following the dynamic block on the Web. World Wide Web 19(6): 1077-1101 (2016) (Download | DOI)
  • Takehiro Yamamoto, Yiqun Liu, Min Zhang, Zhicheng Dou, Ke Zhou, Ilya Markov, Makoto P. Kato, Hiroaki Ohshima, Sumio Fujita. Overview of the NTCIR-12 IMine-2 Task. NTCIR 2016 (Download)
  • Ming Yue, Zhicheng Dou, Sha Hu, Jinxiu Li, Xiao-Jie Wang, Ji-Rong Wen. RUCIR at NTCIR-12 IMINE-2 Task. NTCIR 2016 (Download)
  • Shaoping Ma, Ji-Rong Wen, Yiqun Liu, Zhicheng Dou, Min Zhang, Yi Chang, Xin Zhao. Information Retrieval Technology - 12th Asia Information Retrieval Societies Conference, AIRS 2016, Beijing, China, November 30 - December 2, 2016, Proceedings. Lecture Notes in Computer Science 9994, Springer 2016, ISBN 978-3-319-48050-3 (Download)
2015
  • Zhongqi Lu, Zhicheng Dou*, Xing Xie, Jianxun Lian, Qiang Yang. Content-based Collaborative Filtering for News Topic Recommendation. In Proceedings of Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015), Austin Texas, USA, Jan 25-29, 2015. (AAAI 2015) (CCF A) (Download | DOI)
  • Sha Hu, Zhicheng Dou*, Xiaojie Wang, Tetsuya Sakai, and Ji-Rong Wen. 2015. Search Result Diversification Based on Hierarchical Intents. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (CIKM '15). ACM, New York, NY, USA, 63-72. (CIKM 2015) (CCF B) (Download | DOI)
  • Sha Hu, Zhicheng Dou*, Xiao-Jie Wang, Ji-Rong Wen: Search Result Diversification Based on Query Facets. J. Comput. Sci. Technol. (JCST) 30(4):888-901 (2015) (Download | DOI)
  • Zhicheng Dou and Ji-Rong Wen. Web Analytical Engine in the Big Data Era. Big Data Journal, 2015(3). (In Chinese) (Download | DOI)
↑↑↑↑↑↑After I joined Renmin University of China↑↑↑↑↑↑
2014
  • Yiqun Liu, Ruihua Song, Min Zhang, Zhicheng Dou, Takehiro Yamamoto, Makoto Kato, Hiroaki Ohshima, Ke Zhou. Overview of the NTCIR-11 IMine Task. Proceedings of the 11th NTCIR conference. (Download)
  • Fei Chen, Yiqun Liu, Zhicheng Dou, Keyang Xu, Yujie Cao, Min Zhang, and Shaoping Ma, Revisiting the Evaluation of Diversified Search Evaluation Metrics with User Preferences. Proceedings of the 10th Asia Information Retrieval Society Conference (AIRS 2014) (Download)
  • Jingfei Li, Dawei Song, Peng Zhang, Ji-Rong Wen, and Zhicheng Dou, Personalizing Web Search Results Based on Subspace Projection, Proceedings of the 10th Asia Information Retrieval Society Conference (AIRS 2014) (Download)
  • Shu Tang, Zhicheng Dou, Xing Xie, and Jun He, Detecting and Monitoring Dynamic Content Blocks of a Web Page by Merging its Historical Versions, in SIGIR 2014 Workshop on Temporal, Social and Spatially-aware Information Access (TAIA2014), 2014 (Download)
2013
  • Xiao Ding, Zhicheng Dou, Bing Qin, Ting Liu, and Ji-Rong Wen, Improving Web Search Ranking by Incorporating Structured Annotation of Queries, in Proceedings of EMNLP 2013, pages 468-478, October 2013 (EMNLP 2013) (CCF B) (Download)
  • Kosetsu Tsukuda, Tetsuya Sakai, Zhicheng Dou, and Katsumi Tanaka, Estimating Intent Types for Search Result Diversification, in Information Retrieval Technology, pages 25-37, Springer Berlin Heidelberg, 2013 (Download)
  • Ke Zhou, Tetsuya Sakai, Mounia Lalmas, Zhicheng Dou, and Joemon M. Jose, Evaluating Heterogeneous Information Access, in ACM SIGIR 2013 Workshop on Modeling User Behavior for Information Access Evaluation, 2013 (Download)
  • Qinglei Wang, Yanan Qian, Ruihua Song, Zhicheng Dou, Fan Zhang, Tetsuya Sakai, and Qinghua Zheng, Mining Subtopics from Text Fragments for a Web Query, in Information Retrieval 16(4) pages 484-503, 2013 (Download)
  • Tetsuya Sakai and Zhicheng Dou, Summaries, Ranked Retrieval and Sessions: A Unified Framework for Information Access Evaluation, in Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (SIGIR 2013), pages 473-482, ACM, 2013 (The Best Paper Runner-Up Award) (SIGIR 2013) (CCF A) (Download)
  • Tetsuya Sakai, Zhicheng Dou, and Carles Clarke, The Impact of Intent Selection on Diversified Search Evaluation, in Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (SIGIR 2013), pages 921-924, ACM, 2013 (SIGIR 2013) (CCF A) (Download)
  • Tetsuya Sakai, Zhicheng Dou, Takehiro Yamamoto, Yiqun Liu, Min Zhang, Makoto Kato, Ruihua Song, and Mayu Iwata, Summary of the NTCIR-10 INTENT-2 Task: Subtopic Mining and Search Result Diversification, in Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (SIGIR 2013), pages 761 - 764, ACM, 2013 (SIGIR 2013) (CCF A) (Download)
  • Tetsuya Sakai, Zhicheng Dou, Takehiro Yamamoto, Yiqun Liu, Min Zhang, and Ruihua Song, Overview of the NTCIR-10 INTENT-2 Task, in Proceedings of the 10th NTCIR Conference, pages 94-123, June 18-21, 2013 (Download)
  • Kosetsu Tsukuda, Zhicheng Dou, and Tetsuya Sakai, Microsoft Research Asia at the NTCIR-10 Intent Task, in Proceedings of the 10th NTCIR Conference, June 2013 (Download)
  • Kazuya Narita, Tetsuya Sakai, Zhicheng Dou, and Young-In Song, MSRA at NTCIR-10 1CLICK-2, in Proceedings of the 10th NTCIR Conference, 2013 (Download)
2012
  • Tetsuya Sakai, Zhicheng Dou, Ruihua song, and Noriko Kando, The Reusability of a Diversified Search Test Collection, in Information Retrieval Technology (AIRS 2012), pages 26-38, Springer Berlin Heidelberg, 20 December 2012 (The Best Paper Award) (Download)
2011
  • Zhicheng Dou, Sha Hu, Kun Chen, Ruihua Song, and Ji-Rong Wen, Multi-dimensional Search Result Diversification, in Proceedings of the fourth ACM international conference on Web search and data mining (WSDM 2011), pages 475-484, ACM, February 2011 (WSDM 2011) (CCF B) (Download)
  • Zhicheng Dou, Finding Dimensions for Queries, in Proceedings of the 20th ACM international conference on Information and knowledge management (CIKM 2011), pages 1311-1320, ACM, 2011 (CIKM 2011) (CCF B) (Download)
  • Jialong Han, Qinglei Wang, Naoki Orii, Zhicheng Dou, Tetsuya Sakai, and Ruihua Song, Microsoft Research Asia at the NTCIR-9 Intent Task, in Proceedings of the 10th NTCIR Conference (NTCIR-9), National Institute of Informatics, 2011 (CIKM 2011) (CCF B) (Download)
2010
  • Tetsuya Sakai, Nick Craswell, Ruihua Song, Stephen Robertson, Zhicheng Dou, and Chin-Yew Lin, Simple Evaluation Metrics for Diversified Search Results, in Proceedings of the Third International Workshop on Evaluating Information Access (EVIA), Volumn 26, pages 27, National Institute of Informatics, June 2010 (Download)
  • Ruihua Song, Zhicheng Dou, Hsiao-Wuen Hon, and Yong Yu, Learning Query Ambiguity Models by Using Search Logs, Journal of Computer Science and Technology, 25(4), pages 782-738, Springer, July 2010 (Download)
2009
  • Zhicheng Dou, Kun Chen, Ruihua Song, Yunxiao Ma, Shuming Shi, and Ji-Rong Wen, Microsoft Research Asia at the Web Track of TREC 2009, in Proceedings of TREC 2009, November 2009 (Download)
  • Ji-Rong Wen, Zhicheng Dou, and Ruihua Song, Personalized Web Search, in Encyclopedia of Database Systems, pages 2099-2103, Springer-Verlag, New York, USA, September 2009 (Download)
  • Zhicheng Dou, Ruihua Song, Jian-Yun Nie, and Ji-Rong Wen, Using Anchor Texts with Their Hyperlink Structure for Web Search, in Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval(SIGIR 2009), pages 227-234, ACM, July 2009 (SIGIR 2009) (CCF A) (Download)
  • Zhicheng Dou, Ruihua Song, Ji-Rong Wen, and Xiaojie Yuan, Evaluating the Effectiveness of Personalized Web Search, in IEEE Transactions on Knowledge and Data Engineering (TKDE), 21(8), pages 1178-1190, IEEE computer Society Digital Library, Aug., 2009 (TKDE) (CCF A) (Download)
2008
  • Zhicheng Dou, Ruihua Song, Xiaojie Yuan, and Ji-Rong Wen, Are click-through data adequate for learning web search rankings?, in Proceeding of the 17th ACM conference on Information and knowledge management (CIKM 2008), pages 73-82, ACM, New York, NY, USA, 2008 (CIKM 2008) (CCF B) (Download)
  • Zhicheng Dou, Xiaojie Yuan, and Songbai He, Analysis of Query Repetition in Large-scale Chinese Search Log, Computer Engineering, 34(21), Volumn 21, pages 40-44, 2008 (In Chinese) (Download)
  • Xiaojie Yuan, Zhicheng Dou, Lu Zhang, and Fang Liu, Automatic User Goals Identification Based on Anchor Text and Click-through Data, in Wuhan University Journal of Natural Sciences (WISA2008), 13(4), pages 495-500, 2008 (In Chinese) (Download)
  • Xiaojie Yuan, Zhicheng Dou, Fang Liu, and Lu Zhang, Personalized Web Search Based on Dynamic User Profile, NDBC 2008: Proceedings of the 25th National Database Conference (In Chinese) , 2008 (Download)
  • Lu ZHANG, Xiao-jie YUAN, Fang LIU, and Zhicheng Dou, Research on Distributed Index Mechanism for Large Dataset, Microelectronics & Computer, Volume 10, Pages 037, 2008
2007
  • Zhicheng Dou, Ruihua Song, and Ji-Rong Wen, A large-scale evaluation and analysis of personalized search strategies, in Proceedings of the 16th international conference on World Wide Web (WWW2007), pages 581-590, ACM Press, New York, NY, USA, 2007 (WWW 2007) (CCF A) (Download)

Academic Services

  • Chair/Co-Chair: Sponsorship Co-chair of ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR'18), Program Co-chair (Short Paper) of The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'19), General Co-chair of The 12th Asia Information Retrieval Societies Conference (AIRS'16), Program Co-chair of The 13th Asia Information Retrieval Societies Conference (AIRS'17), Chair of Asia Information Retrieval Societies Steering Committee (2018)
  • Area Chair: CCL 2019, NLPCC 2016
  • Senior PC Member: SIGIR 2018
  • PC Member: SIGIR, KDD, CIKM, WWW, WSDM, IEEE BigData, ICDE, IJCAI, AAAI, EMNLP, NLPCC, CCIR, CCL, CCF BigData, ...
  • Reviewer: TKDE, TOIS, TIST, JMLC, IPM, Neurocomputing, Information Retrieval Journal, DKE, KAIS, JCST, Chinese Journal of Computer
  • Editorial Board: Information Retrieval Journal

Research Projects

Personalized and Diversified Search

Studies show that the vast majority of queries to search engines are short and vague in specifying a user’s intent. Different users may have completely different information needs and goals when using precisely the same query. For example, User A is finding information about Apply Company by issuing a query ``apple'', while User B is finding information related to fruit apple using the same query. When such a query is issued, search engines will return a list of documents that mix different topics. It takes time for a user to choose which information he/she wants, and the search experience in this case is bad. In recent years, I have been working on two different approaches for solving this problem: Personalized Web Search and Search Result Diversification.

  • Personalize Web Search Personalized web search aims to return different search results to different users based upon their interests and preferences. Given the above example query ``query'', a personalized search system tends to just return results about Apple company to user A, or ranks the results about Apple company higher than those about apple fruit. As personalized search will help the user find the information she wants more easily, it is considered as a promising solution to improve the performance of generic web search. My team has designed various personalized search strategies in recent years and advanced the state-of-the-arts in this area.
    • Through a large-scale evaluation and analysis of personalized search strategies (WWW 2007, TKDE 2009), we revealed that personalized search has different impact on different kinds of queries. More specifically, it is effective on queries with large click entropy (likely ambiguious queries), but may hurt queries with small entropy (clear queries).
    • We used hierachical RNN for modeling dynamic user profiles (HRNN:CIKM 2018).
    • We applied generative adversarial networks on personalized search, to solve the problem of limited and noisy click data (PSGAN:SIGIR 2019).
    • More recent works can be found in my publication list......
  • Search Result Diversification:Search Result Diversification is another effective way to solve this problem. Given a query, it aims to provide a list of results that cover as many aspects as possible, so that most users can be satisfied by the top results. Our efforts:
    • Multi-dimensional search result diversification: our multi-dimensional diversification approach generates the best run in TREC 2009 Web Track diversity task.
    • Hierachical search result diversification (Details and Dataset )
    • Search result diversification evaluation (Details and Dataset )
    • Learning to Diversify Search Result via Subtopic Attention (Details and Dataset )
    • To mine better subtopics, we addressed the problem of finding query facets that are multiple groups of words or phrases that explain the underlying information of a query. We have minded query facets by mining and aggregating these significant lists, then used query facets for search result diversification.
    • Getting Ride of Greedy Selection: we propose to take the whole candidate document sequence as input, and simultaneously model the interactions between all candidate documents and directly return their final diversification scores.
    • GIVGAN: we proposed a supervised diversification framework based on Generative Adversarial Network (GAN).
    • More about Search Result Diversification

Query Facet Mining

We address the problem of finding multiple groups of words or phrases that explain the underlying query facets, which we refer to as query dimensions/facets. We assume that the important aspects of a query are usually presented and repeated in the query’s top retrieved documents in the style of lists, and query facets can be mined out by aggregating these significant lists.

My Recent Research Focus: User Centric Information Access

In recent years, with the quick development of mobile phones and network services, most of our daily life activities have been digitized by various devices and applications. There are more and more user generated personal data available, and with the growth of their scale and variety, how to effectively and efficiently accessing these personal information will become more and more challenging. Various applications including search engines and recommendation engines have been developed to help users access public information in the internet, but how to access all personal data in an integrated way is still under investigation. I believe user-centric personalized information access will become more and more important in the near future.

  • Integrating Personalized Search and Diversified Search: Since both Personalized Search and Search Result Diversification are trying to solve the same query ambiguity problem, it is interesting to study how to integrate them in a search engine. Ideally, users need personalized and diversified results.
  • Integrating Search and Recommendation: In recent years, recommender systems have been widely deployed and used by billions of users. Similar to personalized web search, the goal of a recommender system is to return personalized content (such as news, products, videos, pictures, POIs, etc.) to different users. The main different between search and recommendation is the existence of queries in search. Queries are used by users to describe their information need in a search engine while no explicit queries are required in a recommender system. In fact, in some applications, both search and recommendation functions are provided. The core technology used in two services, especially those deep learning based methods proposed in recent years, are becoming similar. The fundamental problem is: can we use the same model simultaneously for both tasks? I am interested in developing unified user profiling and ranking models for integrating search and recommendation tasks.
  • Privacy Protection in User Centric Information Access: Privacy is the most important issue when we leverage intelligent technology to utilize personalized information for information service. There are multiple challenges we need to face when we deliver reliable and secure personalized information access services. Most personalized services rely on high quality user models but these user models are usually built upon personal data which may include sensitive information about users. It is very interesting to train high quality user profiles on the client side without submitting user data to remote servers. I am interested in training shared personalized ranking models with federated learning.
  • Conversational Information Seeking
  • Personalized Chatbot and Intelligent Assistant

I am recruiting students who are interested in the above research topics. Please drop an email to dou at ruc.edu.cn if you want to join my team.

Links