High accuracy retrieval with multiple nested ranker

By Irina Matveeva, C. Burges, Timo Burkard, Andy Laucius, Leon Wong. 2006

151 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Multi-Stage Document Ranking with BERT (2019, background): “This basic approach has received much interest in academia (Matveeva et al., 2006; Wang et al., 2011; Asadi and Lin, 2013; Chen et al., 2017; Mackenzie et al., 2018) as well as industry.”
Anserini (2018, background): “What about reproducibility beyond simple bag-of-words ranking models? Although we have not explicitly addressed this (next) challenge, we believe that baseline bag-of-words ranking models also have an important role to play in modern multi-stage ranking architectures, which have been explored by res”
Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations (2021, background): “In particular, the importance of stable first-stage retrieval within a multi-stage ranking architecture [5, 25, 34] has become even more important, as it provides the foundation for increasingly-complex modern approaches that leverage hybrid techniques.”
Efficient Document Re-Ranking for Transformers by Precomputing Term Representations (2020, background): “These approaches typically act as a final-stage ranking function, via a telescoping (also referred to as cascading, or multi-stage) technique [29, 43]; that is, initial ranking is conducted with less expensive approaches (e.”
Learning (predictive) risk scores in the presence of censoring due to interventions (2015, methodology): “Additional approaches include FRank (Tsai et al, 2007), nested ranker (Matveeva et al, 2006), and multiple hyperplane ranker (Qin et al, 2007).”
Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks (2019, methodology): “Any loss in retrieval effectiveness due to incorporating strong query term independence assumptions may be further recovered by additional stages of re-ranking in a telescoping approach [Matveeva et al., 2006].”
Direct Learning to Rank and Rerank (2018, background): “…ranking water pipes in order of vulnerability (as considered by Li et al, 2013), other areas of information retrieval (Xu, 2007; Cao et al, 2007; Matveeva et al, 2006; Lafferty and Zhai, 2001; Li et al, 2007) and in almost any domain where one measures the quality of results by rank statistics.”
A Dual Embedding Space Model for Document Ranking (2016, methodology): “2, there is a parallel between this experiment setup and the telescoping [27] evaluation strategy, and has been used often in recent literature (e.”
Learning to Rank with Nonsmooth Cost Functions (2006, methodology): “The ranking problem itself has attracted increasing attention recently (see for example [4, 2, 8]), and in this paper we will use the RankNet algorithm of [2] as a baseline, since it is both easy to implement and performs well on large retrieval tasks.”
Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension (2018, methodology): “It is diﬃcult to adapt neural networks to the whole of a large-scale corpus due to their computational cost; so, we consider using a telescoping setting that uses chaining of diﬀerent IR models, where each successive model re-ranks a smaller number of passages [27].”
Overview of the TREC 2020 Deep Learning Track (2021, background): “This is a common scenario in many real-world retrieval systems that employ a telescoping architecture [Matveeva et al., 2006, Wang et al., 2011].”
Linear feature-based models for information retrieval (2007, background): “A RankNet is trained using gradient descent over a differentiable cost function.”
LETOR: Benchmark Dataset for Research on Learning to Rank for Information Retrieval (2007, background): “Because of the it offers , learning to rank been gain ed increasing attention in IR Many methods have been proposed (e.g., [2] , [5] , [6] , [7] , [10] , [16] , [20] , [ 22 ] , [23] ) and applied to IR applications (e.g., [3] , [12] , [27] , [31] , [32] , [33] ). Unfortunately , the experimental res”
Learning to rank for information retrieval (2009, unknown): “In [84], a nested ranker is built on top of RankNet to further improve the retrieval performance.”
Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset (2020, background): “Multi-stage search architectures represent the most common design for modern search engines, with work in academia dating back over a decade (Matveeva et al., 2006; Wang et al., 2011; Asadi and Lin, 2013).”
Fine-Tuning LLaMA for Multi-Stage Text Retrieval (2023, background): “While multi-stage retrieval pipelines date back well over a decade (Matveeva et al., 2006; Cambazoglu et al., 2010; Wang et al., 2011), they have bene-”
TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime (2021, background): “This is a common scenario in many real-world retrieval systems that employ a telescoping architecture [15, 25].”
An Introduction to Neural Information Retrieval (2018, unknown): “The chaining of different IR models where each successive model re-ranks a smaller number of candidate documents is called Telescoping [Matveeva et al., 2006].”