Smoothing clickthrough data for web search ranking

Gao, Jianfeng; Yuan, Wei; Xiao, Liping; Deng, Kefeng; Nie, Jian‐Yun

doi:10.1145/1571941.1572003

Cited by 72 publications

(79 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, the click-through data includes a score that is derived from the number of clicks the query yields for a single document. Gao et al [15] follow a similar approach, but add smoothing to click-through data to counter sparsity issues. Amitay et al [1] study the effectiveness of query reformulations for document expansion by appending all queries in a reformulation session to the top-k returned documents for the last query.…”

Section: Document Expansionmentioning

confidence: 99%

Dynamic Collective Entity Representations for Entity Ranking

Graus

Tsagkias²,

Weerkamp³

et al. 2016

Proceedings of the Ninth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Dynamic collective entity representations for entity rankingGraus, D.P.; Tsagkias, E.; Weerkamp, W.; Meij, E.J.; de Rijke, M. General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. ABSTRACTEntity ranking, i.e., successfully positioning a relevant entity at the top of the ranking for a given query, is inherently difficult due to the potential mismatch between the entity's description in a knowledge base, and the way people refer to the entity when searching for it. To counter this issue we propose a method for constructing dynamic collective entity representations. We collect entity descriptions from a variety of sources and combine them into a single entity representation by learning to weight the content from different sources that are associated with an entity for optimal retrieval effectiveness. Our method is able to add new descriptions in real time and learn the best representation as time evolves so as to capture the dynamics of how people search entities. Incorporating dynamic description sources into dynamic collective entity representations improves retrieval effectiveness by 7% over a state-ofthe-art learning to rank baseline. Periodic retraining of the ranker enables higher ranking effectiveness for dynamic collective entity representations.

show abstract

Section: Document Expansionmentioning

confidence: 99%

Dynamic Collective Entity Representations for Entity Ranking

Graus

Tsagkias²,

Weerkamp³

et al. 2016

Proceedings of the Ninth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…In (Xu et al, 2010), a method is proposed, which automatically detects judgment errors by using the click-through data. The sparseness of the click-through data is a major challenge in learning to rank approaches that have been investigated by researchers such as (Gao et al, 2009). They have proposed two techniques for expanding clickthrough features in order to address the sparseness.…”

Section: Related Workmentioning

confidence: 99%

Learning to rank with click-through features in a reinforcement learning framework

Keyhanipour

Moshiri

Piroozmand

et al. 2016

IJWIS

View full text Add to dashboard Cite

Purpose Learning to rank algorithms inherently faces many challenges. The most important challenges could be listed as high-dimensionality of the training data, the dynamic nature of Web information resources and lack of click-through data. High dimensionality of the training data affects effectiveness and efficiency of learning algorithms. Besides, most of learning to rank benchmark datasets do not include click-through data as a very rich source of information about the search behavior of users while dealing with the ranked lists of search results. To deal with these limitations, this paper aims to introduce a novel learning to rank algorithm by using a set of complex click-through features in a reinforcement learning (RL) model. These features are calculated from the existing click-through information in the data set or even from data sets without any explicit click-through information. Design/methodology/approach The proposed ranking algorithm (QRC-Rank) applies RL techniques on a set of calculated click-through features. QRC-Rank is as a two-steps process. In the first step, Transformation phase, a compact benchmark data set is created which contains a set of click-through features. These feature are calculated from the original click-through information available in the data set and constitute a compact representation of click-through information. To find most effective click-through feature, a number of scenarios are investigated. The second phase is Model-Generation, in which a RL model is built to rank the documents. This model is created by applying temporal difference learning methods such as Q-Learning and SARSA. Findings The proposed learning to rank method, QRC-rank, is evaluated on WCL2R and LETOR4.0 data sets. Experimental results demonstrate that QRC-Rank outperforms the state-of-the-art learning to rank methods such as SVMRank, RankBoost, ListNet and AdaRank based on the precision and normalized discount cumulative gain evaluation criteria. The use of the click-through features calculated from the training data set is a major contributor to the performance of the system. Originality/value In this paper, we have demonstrated the viability of the proposed features that provide a compact representation for the click through data in a learning to rank application. These compact click-through features are calculated from the original features of the learning to rank benchmark data set. In addition, a Markov Decision Process model is proposed for the learning to rank problem using RL, including the sets of states, actions, rewarding strategy and the transition function.

show abstract

“…Together, they submitted a total of 679,808 queries in 67,812 sessions. Session boundaries are drawn based on a 30-minute threshold of user inactivity as suggested by several previous studies (e.g., [9,10]). Since this work is concerned with information seeking behavior, we exclude navigational queries from our inspection in order to get a clearer impression of the difference between normal and atypical informational queries.…”

Section: Data Setmentioning

confidence: 99%

Personalizing atypical web search sessions

Eickhoff

Collins-Thompson

Bennett

et al. 2013

Proceedings of the Sixth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Most research in Web search personalization models users as static or slowly evolving entities with a given set of preferences defined by their past behavior. However, recent publications as well as empirical evidence suggest that for a significant number of search sessions, users diverge from their regular search profiles in order to satisfy atypical, limitedduration information needs. In this work, we conduct a large-scale inspection of real-life search sessions to further understand this scenario. Subsequently, we design an automatic means of detecting and supporting such atypical sessions. We demonstrate significant improvements over stateof-the-art Web search personalization techniques by accounting for the typicality of search sessions. The proposed method is evaluated based on Web-scale search session data spanning several months of user activity.

show abstract

Smoothing clickthrough data for web search ranking

Cited by 72 publications

References 21 publications

Dynamic Collective Entity Representations for Entity Ranking

Dynamic Collective Entity Representations for Entity Ranking

Learning to rank with click-through features in a reinforcement learning framework

Personalizing atypical web search sessions

Contact Info

Product

Resources

About