adaQAC: Adaptive Query Auto-Completion via Implicit Negative Feedback

Query auto-completion (QAC) facilitates user query composition by suggesting queries given query prefix inputs. In 2014, global users of Yahoo! Search saved more than 50% keystrokes when submitting English queries by selecting suggestions of QAC. Users' preference of queries can be inferred during user-QAC interactions, such as dwelling on suggestion lists for a long time without selecting query suggestions ranked at the top. However, the wealth of such implicit negative feedback has not been exploited for designing QAC models. Most existing QAC models rank suggested queries for given prefixes based on certain relevance scores. We take the initiative towards studying implicit negative feed- back during user-QAC interactions. This motivates re-designing QAC in the more general "(static) relevance"(adaptive) implicit negative feedback? framework. We propose a novel adaptive model adaQAC that adapts query auto-completion to users' implicit negative feedback towards unselected query suggestions. We collect user-QAC interaction data and perform large-scale experiments. Empirical results show that implicit negative feedback significantly and consistently boosts the accuracy of the investigated static QAC models that only rely on relevance scores. Our work compellingly makes a key point: QAC should be designed in a more general framework for adapting to implicit negative feedback.

[1]  Gerard Salton,et al.  The SMART Retrieval System—Experiments in Automatic Document Processing , 1971 .

[2]  Bhaskar Mitra,et al.  An Eye-tracking Study of User Interactions with Query Auto Completion , 2014, CIKM.

[3]  ChengXiang Zhai,et al.  Improving retrieval accuracy of difficult queries through generalizing negative document language models , 2011, CIKM '11.

[4]  Grace Hui Yang,et al.  Win-win search: dual-agent stochastic game in session search , 2014, SIGIR.

[5]  Craig MacDonald,et al.  User model-based metrics for offline query suggestion evaluation , 2013, SIGIR.

[6]  ChengXiang Zhai,et al.  Improve retrieval accuracy for difficult queries using negative feedback , 2007, CIKM '07.

[7]  Giuseppe Ottaviano,et al.  Space-efficient data structures for Top-k completion , 2013, WWW '13.

[8]  R. Steele.  Optimization , 2005 .

[9]  Susan T. Dumais,et al.  Understanding temporal query dynamics , 2011, WSDM '11.

[10]  Filip Radlinski,et al.  On user interactions with query auto-completion , 2014, SIGIR.

[11]  Guoliang Li,et al.  Efficient interactive fuzzy keyword search , 2009, WWW '09.

[12]  Pu-Jen Cheng,et al.  Learning user reformulation behavior for query auto-completion , 2014, SIGIR.

[13]  Yuefeng Li,et al.  Mining Specific and General Features in Both Positive and Negative Relevance Feedback: QUT E-Discovery Lab at the TREC 2010 Relevance Feedback Track , 2009, TREC.

[14]  Kunihiko Sadakane,et al.  Efficient Error-tolerant Query Autocompletion , 2013, Proc. VLDB Endow..

[15]  Hongbo Deng,et al.  A two-dimensional click model for query auto-completion , 2014, SIGIR.

[16]  Song Hua,et al.  Negative Feedback: The Forsaken Nature Available for Re-ranking , 2010, COLING.

[17]  Xin-She Yang,et al.  Introduction to Algorithms , 2021, Nature-Inspired Optimization Algorithms.

[18]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[19]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[20]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[21]  ChengXiang Zhai,et al.  A study of methods for negative relevance feedback , 2008, SIGIR '08.

[22]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[23]  Jun-yi Wang,et al.  The Study of Methods for Language Model Based Positive and Negative Relevance Feedback in Information Retrieval , 2010, 2012 Fourth International Symposium on Information Science and Engineering.

[24]  Milad Shokouhi,et al.  Time-sensitive query auto-completion , 2012, SIGIR '12.

[25]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[26]  Ziv Bar-Yossef,et al.  Context-sensitive query auto-completion , 2011, WWW.

[27]  Susan T. Dumais,et al.  Towards Supporting Search over Trending Events with Social Media , 2013, ICWSM.

[28]  Grace Hui Yang,et al.  Utilizing query change for session search , 2013, SIGIR.

[29]  Jun Wang,et al.  Dynamic Information Retrieval Modeling , 2015, Synthesis Lectures on Information Concepts, Retrieval, and Services.

[30]  Huizhong Duan,et al.  Online spelling correction for query completion , 2011, WWW.

[31]  Surajit Chaudhuri,et al.  Extending autocompletion to tolerate errors , 2009, SIGMOD Conference.

[32]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[33]  Brian N. Bershad,et al.  Why we search: visualizing and predicting user behavior , 2007, WWW '07.

[34]  M. de Rijke,et al.  Time-sensitive Personalized Query Auto-Completion , 2014, CIKM.

[35]  Milad Shokouhi,et al.  Learning to personalize query auto-completion , 2013, SIGIR.

[36]  Tetsuya Sakai,et al.  Time-aware structured query suggestion , 2013, SIGIR.

[37]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[38]  Shuang-Hong Yang,et al.  Collaborative competitive filtering: learning recommender using context of user choice , 2011, SIGIR.

[39]  Hongfei Lin,et al.  A Multiple Relevance Feedback Strategy with Positive and Negative Models , 2014, PloS one.

[40]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[41]  Joemon M. Jose,et al.  Recent and robust query auto-completion , 2014, WWW.