{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ranking-for-relevance-and-display-preferences","title":"Ranking for Relevance and Display Preferences in Complex Presentation Layouts","arxiv_id":"1805.02404","date":"2018-05-07","proceeding":null,"authors":["Harrie Oosterhuis","Maarten de Rijke"],"abstract":"Learning to Rank has traditionally considered settings where given the\nrelevance information of objects, the desired order in which to rank the\nobjects is clear. However, with today's large variety of users and layouts this\nis not always the case. In this paper, we consider so-called complex ranking\nsettings where it is not clear what should be displayed, that is, what the\nrelevant items are, and how they should be displayed, that is, where the most\nrelevant items should be placed. These ranking settings are complex as they\ninvolve both traditional ranking and inferring the best display order. Existing\nlearning to rank methods cannot handle such complex ranking settings as they\nassume that the display order is known beforehand. To address this gap we\nintroduce a novel Deep Reinforcement Learning method that is capable of\nlearning complex rankings, both the layout and the best ranking given the\nlayout, from weak reward signals. Our proposed method does so by selecting\ndocuments and positions sequentially, hence it ranks both the documents and\npositions, which is why we call it the Double-Rank Model (DRM). Our experiments\nshow that DRM outperforms all existing methods in complex ranking settings,\nthus it leads to substantial ranking improvements in cases where the display\norder is not known a priori.","url_abs":"http://arxiv.org/abs/1805.02404v1","url_pdf":"http://arxiv.org/pdf/1805.02404v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ranking-for-relevance-and-display-preferences","repo_url":"https://github.com/HarrieO/RankingComplexLayouts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}