Search-based structured prediction

Abstract

We present Searn, an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. Searn is a meta-algorithm that transforms these complex problems into simple classification problems to which any binary classifier may be applied. Unlike current algorithms for structured learning that require decomposition of both the loss function and the feature functions over the predicted structure, Searn is able to learn prediction functions for any loss function and any class of features. Moreover, Searn comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies good performance on the structured prediction problem.

DOI: 10.1007/s10994-009-5106-x

Extracted Key Phrases

6 Figures and Tables

020406020072008200920102011201220132014201520162017
Citations per Year

326 Citations

Semantic Scholar estimates that this publication has 326 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Daum2009SearchbasedSP, title={Search-based structured prediction}, author={Hal Daum{\'e} and John Langford and Daniel Marcu}, journal={Machine Learning}, year={2009}, volume={75}, pages={297-325} }