Optimum polynomial retrieval functions based on the probability ranking principle

By Norbert Fuhr. 1989

Subfields: Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

Citations in the corpus

Learning to summarize from human feedback (2020, methodology): “Our reward modeling approach was developed in prior work on learning to rank [40], which has been applied to ranking search results using either explicit feedback [2, 18] or implicit feedback in the form of click-through data [29, 30].”
Test Collection Based Evaluation of Information Retrieval Systems (2010, background): “The study of LTR has its origins in the late 1980s [89]; see [168] for other early LTR papers.”
An Introduction to Neural Information Retrieval (2018, unknown): “1) where, s(~xq,d) is the score predicted by the model and relq(d) can either be the value of the relevance label [Cossock and Zhang, 2006] or the one-hot representation when the label is categorical [Fuhr, 1989].”
Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web search (2007, background): “and Joachims [2005]. The base of comparison is either the explicit judgments of the abstracts or the explicit judgments of the page itself.”
Optimizing search engines using clickthrough data (2002, background): “Φ(q, d) is a mapping onto features that describe the match between query q and document d like in the description-oriented retrieval approach of Fuhr et al. [10][11].”
Mining Query Logs: Turning Search Usage Data into Knowledge (2010, unknown): “where w is a weight vector that is the one learnt by the learning algorithm, and Φ(q,d) is a mapping onto features describing the matching of query q and document d: much in the spirit of Fuhr [82] and Fuhr et al.”
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, methodology): “In an early attempt on L2R, Fuhr [70] adopted a linear regression with a polynomial feature expansion to learn the score function f (x).”
Measuring Retrieval Effectiveness Based on User Preference of Documents (1995, background): “It is important to ascertain how to use this measure when only partial user preference information is given (Frei & Schäuble, 1991; Fuhr, 1989).”
TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank (2018, background): “Pointwisemethods [13, 17, 18] approximate ranking to a classification or regression problem and as such attempt to optimize the discrepancy between individual ground-truth labels and the absolute magnitude of relevance scores produced by the learning-torank model.”
Learning to rank for information retrieval (2009, unknown): “In recent years, learning to rank has become a very hot research direction in IR, and a large number of learning-to-rank algorithms have been proposed, such as [9, 13, 14, 16, 17, 26, 29, 33, 34, 47, 49, 59, 63, 73, 78, 90, 97, 99, 102, 114, 119, 122, 129, 134, 136].”