Predicting diverse subsets using structural SVMs

By Yisong Yue, Thorsten Joachims. 2008

174 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

Citations in the corpus

Determinantal Point Processes for Machine Learning (2012, neutral): “…a number of recently developed techniques for working with diverse sets, particularly in the information retrieval community [Carbonell and Goldstein, 1998, Zhai et al., 2003, Chen and Karger, 2006, Yue and Joachims, 2008, Radlinski et al., 2008, Swaminathan et al., 2009, Raman et al., 2012].”
Learning to Diversify from Implicit Feedback (2012, methodology): “To ensure difference in feedback between the two user utility functions, we weight the different intents (as done in [15]), which results in the utility being higher if a more popular topic is covered instead of a less popular one.”
Near-Optimal MAP Inference for Determinantal Point Processes (2012, background): “Informative subset selection problems arise in many applications where a small number of items must be chosen to represent or cover a much larger set; for instance, text summarization [1, 2], document and image search [3, 4, 5], sensor placement [6], viral marketing [7], and many others.”
Diverse M-Best Solutions in Markov Random Fields (2012, background): “Yu and Joachims [39] proposed to learn a predictor that selects a topic-diverse subset of documents.”
k-DPPs: Fixed-Size Determinantal Point Processes (2011, methodology): “…for simple probabilistic models of relevance (Chen & Karger, 2006), multi-armed bandit exploration/exploitation models (Radlinski et al., 2008), structured prediction models learned using structural SVMs (Yue & Joachims, 2008), and submodular optimization for blog search (El-Arini et al., 2009).”
Detecting duplicate web documents using clickthrough data (2011, background): “…Emine Yilmaz Microsoft Microsoft Research Microsoft 840 Cambie Street 1 Microsoft Way 7 J J Thomson Ave Vancouver, BC, CanadaRedmond, WA, USACambridge, UK .liprad@microsoft.com pauben@microsoft.com eminey@microsoft.com ABSTRACT The web contains many duplicate and near-duplicate documents.”
Interactively optimizing information retrieval systems as a dueling bandits problem (2009, methodology): “Our framework is extendable in many ways, such as integrating pairwise document preferences (Joachims et al., 2007; Carterette et al., 2008), and diversity ( Yue & Joachims, 2008; Radlinski et al., 2008a).”
Online learning to diversify from implicit feedback (2012, methodology): “In particular, we compare against the one-level version of the method proposed in [12], which is a generalization of [18].”