Optimizing search engines using clickthrough data

Joachims, Thorsten

doi:10.1145/775066.775067

Cited by 1,223 publications

(2,065 citation statements)

References 0 publications

Supporting

Mentioning

2,054

Contrasting

Unclassified

Order By: Relevance

“…This square measure analogous to the pill servers in Bigtable [27], and own disjoint partitions of the database. Associate in Nursing OTM is to blame for all the concurrency management and recovery practicality for the partitions it owns.…”

Section: Owning Dealing Managersmentioning

confidence: 99%

Associate Adaptable Transactional Information Store in the Cloud Using Distributed Storage and Meta Data Manager

Venkatesan¹

2015

IJIRCCE

View full text Add to dashboard Cite

ABSTRACT:Over the last few years, "Cloud Computing" or "Elastic Computing" has emerged as a compelling and successful paradigm for net scale computing. One of the key causative factors to the current success is that the elasticity of resources. In spite of the snap provided by the infrastructure and therefore the scalable style of the applications, the elephant (or the underlying database), which drives most of those web-based applications, is not terribly elastic and scalable, and thus limits measurability. In this paper, we have a tendency to propose Adaptable transactional that addresses this issue of measurability and snap of the info store during a cloud computing setting to leverage from the elastic nature of the underlying infrastructure, whereas providing scalable transactional knowledge access. This paper aims at providing the planning of a system current; highlight the major style selections, analysing the various guarantees provided by the system, and distinguishing several vital challenges for the analysis community striving for computing within the cloud.

show abstract

Section: Owning Dealing Managersmentioning

confidence: 99%

Associate Adaptable Transactional Information Store in the Cloud Using Distributed Storage and Meta Data Manager

Venkatesan¹

2015

IJIRCCE

View full text Add to dashboard Cite

show abstract

“…Google or Naver), it returns an ordered set of documents according to the computed relevances. In the IR system the relevances is estimated using the click-through data (Joachims, 2003), which is an implicit feedback to the list of documents. Figure 2.1 shows the process of cumulating the click-through data in the IR system.…”

Section: Thurstone Model For Ranking Without Covariatesmentioning

confidence: 99%

“…The RankSVM (Joachims, 2003) uses the hinge loss function as the surrogated loss function. RankNet (Burges et al, 2005) and Rankboost (Freund et al, 2003) adopt the logistic loss function and exponential loss function, respectively.…”

Section: Application To Information Retrieval Systemmentioning

confidence: 99%

“…When only linear models are considered, Fisher consistency does not hold in general. However, through the proof of Theorem 3.1, we know that the estimators of the regression coefficients obtained from the methods based on pairwise comparison, RankSVM (Joachims, 2003), RankNet (Burges et al, 2005), and Rankboost (Freund et al, 2003), are consistent up to scale when F is linear function class. Hence, we can estimate the relevances of documents consistently.…”

Section: Application To Information Retrieval Systemmentioning

confidence: 99%

“…In statistics a lot of probability models for ranking are developed such as the Thurstone model (Thurstone, 1927), the Bradley-Terry model (Bradley and Terry, 1952), the Luce model (Luce, 1959), Mallows' φ−model (Mallows, 1957), gamma ranking model (Stern, 1990), distance based ranking model (Flinger and Verducci, 1986). A ranking model for IR based on the Bradley-Terry model is proposed by many researchers (Joachims, 2003;Freund et al, 2003;Burges et al, 2005;Xia et al, 2008). The popularity of the BradleyTerry model is due to its resemblance to the logistic regression model and computational advantages (Yan et al, 2010;Hong et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Revisiting the Bradley-Terry model and its application to information retrieval

Jeon¹,

Kim²

2013

Journal of the Korean Data and Information Science Society

View full text Add to dashboard Cite

The Bradley-Terry model is widely used for analysis of pairwise preference data. We explain that the popularity of Bradley-Terry model is gained due to not only easy computation but also some nice asymptotic properties when the model is misspecified. For information retrieval required to analyze big ranking data, we propose to use a pseudo likelihood based on the Bradley-Terry model even when the true model is different from the Bradley-Terry model. We justify using the Bradley-Terry model by proving that the estimated ranking based on the proposed pseudo likelihood is consistent when the true model belongs to the class of Thurstone models, which is much bigger than the Bradley-Terry model.

show abstract

Evaluating the effectiveness of and patterns of interactions with automated searching assistance

Jansen

McNeese

2005

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

We report quantitative and qualitative results of an empirical evaluation to determine whether automated assistance improves searching performance and when searchers desire system intervention in the search process. Forty participants interacted with two fully functional information retrieval systems in a counterbalanced, within-participant study. The systems were identical in all respects except that one offered automated assistance and the other did not. The study used a client-side automated assistance application, an approximately 500,000-document Text REtrieval Conference content collection, and six topics. Results indicate that automated assistance can improve searching performance. However, the improvement is less dramatic than one might expect, with an approximately 20% performance increase, as measured by the number of userselected relevant documents. Concerning patterns of interaction, we identified 1,879 occurrences of searchersystem interactions and classified them into 9 major categories and 27 subcategories or states. Results indicate that there are predictable patterns of times when searchers desire and implement searching assistance. The most common three-state pattern is Execute Query-View Results: With Scrolling-View Assistance. Searchers appear receptive to automated assistance; there is a 71% implementation rate. There does not seem to be a correlation between the use of assistance and previous searching performance. We discuss the implications for the design of information retrieval systems and future research directions.

show abstract

Optimizing search engines using clickthrough data

Cited by 1,223 publications

References 0 publications

Associate Adaptable Transactional Information Store in the Cloud Using Distributed Storage and Meta Data Manager

Associate Adaptable Transactional Information Store in the Cloud Using Distributed Storage and Meta Data Manager

Revisiting the Bradley-Terry model and its application to information retrieval

Evaluating the effectiveness of and patterns of interactions with automated searching assistance

Contact Info

Product

Resources

About