ABSTRACT
Learning to Rank has traditionally considered settings where given the relevance information of objects, the desired order in which to rank the objects is clear. However, with today's large variety of users and layouts this is not always the case. In this paper, we consider so-called complex ranking settings where it is not clear what should be displayed, that is, what the relevant items are, and how they should be displayed, that is, where the most relevant items should be placed. These ranking settings are complex as they involve both traditional ranking and inferring the best display order. Existing learning to rank methods cannot handle such complex ranking settings as they assume that the display order is known beforehand. To address this gap we introduce a novel Deep Reinforcement Learning method that is capable of learning complex rankings, both the layout and the best ranking given the layout, from weak reward signals. Our proposed method does so by selecting documents and positions sequentially, hence it ranks both the documents and positions, which is why we call it the Double Rank Model (DRM). Our experiments show that DRM outperforms all existing methods in complex ranking settings, thus it leads to substantial ranking improvements in cases where the display order is not known a priori.
- Peter Bailey, Nick Craswell, Ryen W. White, Liwei Chen, Ashwin Satyanarayana, and S.M.M. Tahaghoghi . 2010. Evaluating whole-page relevance. In SIGIR. ACM, 767--768. Google ScholarDigital Library
- Georg Buscher, Susan Dumais, and Edward Cutrell . 2010. The good, the bad, and the random: an eye-tracking study of ad quality in web search SIGIR. ACM, 42--49. Google ScholarDigital Library
- Matthew Campion . 2013. Amazon.com product search and navigation eye tracking study. https://www.looktracker.com/blog/eye-tracking-case-study/amazon-com-product-search-and-navigation-eye-tracking-study/.Google Scholar
- Olivier Chapelle and Yi Chang . 2011. Yahoo! Learning to Rank Challenge Overview. Journal of Machine Learning Research Vol. 14 (2011), 1--24.Google ScholarDigital Library
- Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio . 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014).Google Scholar
- Aleksandr Chuklin and Maarten de Rijke . 2016. Incorporating clicks, attention and satisfaction into a search engine result page evaluation model. In CIKM. ACM, 175--184. Google ScholarDigital Library
- Domenico Dato, Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Nicola Tonellotto, and Rossano Venturini . 2016. Fast ranking with additive ensembles of oblivious and non-oblivious regression trees. ACM Transactions on Information Systems Vol. 35, 2 (2016), Article 15. Google ScholarDigital Library
- Nikhil R. Devanur, Zhiyi Huang, Nitish Korula, and Vahab S. Mirrokni . 2016. Whole-page optimization and submodular welfare maximization with online bidders. ACM Transactions on Economics and Comput. Vol. 4, 3 (2016), Article 14. Google ScholarDigital Library
- Sepp Hochreiter and Jürgen Schmidhuber . 1997. Long short-term memory. Neural Computation Vol. 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Gord Hotchkiss, Steve Alston, and Greg Edwards . 2005. Eye tracking study. Research white paper, Enquiro Search Solutions Inc..Google Scholar
- Bernard J. Jansen, Anna Brown, and Marc Resnick . 2007. Factors relating to the decision to click on a sponsored link. Decision Support Systems Vol. 44, 1 (2007), 46--59. Google ScholarDigital Library
- Thorsten Joachims, Laura Granka, Bing Pan, Helene Hembrooke, Filip Radlinski, and Geri Gay . 2007. Evaluating the accuracy of implicit feedback from clicks and query reformulations in web search. ACM Transactions on Information Systems Vol. 25, 2 (2007), Article 7. Google ScholarDigital Library
- Alexandros Karatzoglou, Linas Baltrunas, and Yue Shi . 2013. Learning to rank for recommender systems. In RecSys. ACM, 493--494. Google ScholarDigital Library
- Shubhra Kanti Karmaker Santu, Parikshit Sondhi, and ChengXiang Zhai . 2017. On application of learning to rank for e-commerce search SIGIR. ACM, 475--484. Google ScholarDigital Library
- Damien Lefortier, Adith Swaminathan, Xiaotiao Gu, Thorsten Joachims, and Maarten de Rijke . 2016. Large-scale validation of counterfactual learning methods: A test-bed NIPS Workshop on Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems.Google Scholar
- Long-H Lin . 1992. Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine learning Vol. 8, 3/4 (1992), 69--97. Google ScholarDigital Library
- Tie-Yan Liu . 2009. Learning to rank for information retrieval. Foundations and Trends in Information Retrieval Vol. 3, 3 (2009), 225--331. Google ScholarDigital Library
- Wanxuan Lu and Yunde Jia . 2014. An eye-tracking study of user behavior in web image search PRICAI 2014: Trends in Artificial Intelligence. Springer.Google Scholar
- Cheng Luo, Yiqun Liu, Tetsuya Sakai, Fan Zhang, Min Zhang, and Shaoping Ma . 2017. Evaluating mobile search with height-biased gain. In SIGIR. ACM, 435--444. Google ScholarDigital Library
- Pavel Metrikov, Fernando Diaz, Sebastien Lahaie, and Justin Rao . 2014. Whole page optimization: How page elements interact with the position auction EC. ACM, 583--600. Google ScholarDigital Library
- Eleni Michailidou, Christoforos Christoforou, and Panayiotis Zaphiris . 2014. Towards predicting ad effectiveness via an eye tracking study International Conference on HCI in Business. Springer, 670--680.Google Scholar
- Volodymyr Mnih and et al. . 2015. Human-level control through deep reinforcement learning. Nature Vol. 518 (25 02 . 2015), 529 EP --.Google Scholar
- Tao Qin and Tie-Yan Liu . 2013. Introducing LETOR 4.0 Datasets. CoRR Vol. abs/1306.2597 (2013). deftempurl%http://arxiv.org/abs/1306.2597 tempurlGoogle Scholar
- Guy Redwood . 2009. Eye tracking analysis. Internet Retailing Vol. 3, 3 (2009), 17. http://www.simpleusability.com/wp-content/uploads/2010/07/amazon-eye-tracking-review.pdfGoogle Scholar
- Richard S. Sutton and Andrew G. Barto . 1998. Reinforcement Learning: An Introduction. MIT Press, Cambridge. Google ScholarDigital Library
- Yukihiro Tagami, Shingo Ono, Koji Yamamoto, Koji Tsukamoto, and Akira Tajima . 2013. CTR prediction for contextual advertising: Learning-to-rank approach Proceedings of the Seventh International Workshop on Data Mining for Online Advertising. ACM, New York, NY, USA, Article 4. Google ScholarDigital Library
- Hado Van Hasselt, Arthur Guez, and David Silver . 2016. Deep reinforcement learning with double Q-learning AAAI. 2094--2100. Google ScholarDigital Library
- Yue Wang, Dawei Yin, Luo Jie, Pengyuan Wang, Makoto Yamada, Yi Chang, and Qiaozhu Mei . 2016. Beyond ranking: Optimizing whole-page presentation WSDM. ACM, 103--112. Google ScholarDigital Library
- Zeng Wei, Jun Xu, Yanyan Lan, Jiafeng Guo, and Xueqi Cheng . 2017. Reinforcement learning to rank with Markov decision process SIGIR. ACM, 945--948. Google ScholarDigital Library
- Long Xia, Jun Xu, Yanyan Lan, Jiafeng Guo, Wei Zeng, and Xueqi Cheng . 2017. Adapting Markov decision process for search result diversification SIGIR. ACM, 535--544. Google ScholarDigital Library
- Xiaohui Xie, Yiqun Liu, Maarten de Rijke, Jiyin He, Min Zhang, and Shaoping Ma . 2018. Why people search for images using web search engines WSDM. ACM, 655--663. Google ScholarDigital Library
- Xiaohui Xie, Yiqun Liu, Xiaochuan Wang, Meng Wang, Zhijing Wu, Yingying Wu, Min Zhang, and Shaoping Ma . 2017. Investigating examination behavior of image search users SIGIR. ACM, 275--284. Google ScholarDigital Library
Index Terms
- Ranking for Relevance and Display Preferences in Complex Presentation Layouts
Recommendations
Ranking Relevance in Yahoo Search
KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningSearch engines play a crucial role in our daily lives. Relevance is the core problem of a commercial search engine. It has attracted thousands of researchers from both academia and industry and has been studied for decades. Relevance in a modern search ...
Quality-biased ranking for queries with commercial intent
WWW '13 Companion: Proceedings of the 22nd International Conference on World Wide WebModern search engines are good enough to answer popular commercial queries with mainly highly relevant documents. However, our experiments show that users behavior on such relevant commercial sites may differ from one to another web-site with the same ...
Extracting search-focused key n-grams for relevance ranking in web search
WSDM '12: Proceedings of the fifth ACM international conference on Web search and data miningIn web search, relevance ranking of popular pages is relatively easy, because of the inclusion of strong signals such as anchor text and search log data. In contrast, with less popular pages, relevance ranking becomes very challenging due to a lack of ...
Comments