Learning structural SVMs with latent variables
Authors:
Open Access
- 14 June 2009
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1169-1176
Abstract
We present a large-margin formulation and algorithm for structured output prediction that allows the use of latent variables. Our proposal covers a large range of application problems, with an optimization problem that can be solved efficiently using Concave-Convex Programming. The generality and performance of the approach is demonstrated through three applications including motiffinding, noun-phrase coreference resolution, and optimizing precision at k in information retrieval.Keywords
Funding Information
- Division of Information and Intelligent Systems (IIS-0713483)
This publication has 17 references indexed in Scilit:
- Cutting-plane training of structural SVMsMachine Learning, 2009
- GIMSAN: a Gibbs motif finder with significance analysisBioinformatics, 2008
- Learning to rank2007
- Supervised clustering with support vector machines2005
- The Concave-Convex ProcedureNeural Computation, 2003
- Optimizing search engines using clickthrough data2002
- Improving machine learning approaches to coreference resolution2001
- A model-theoretic coreference scoring scheme1995
- Unsupervised learning of multiple motifs in biopolymers using expectation maximizationMachine Learning, 1995
- Proximity control in bundle methods for convex nondifferentiable minimizationMathematical Programming, 1990