Search-based Structured Prediction. (arXiv:0907.0786v1 [cs.LG])

1. 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 ... (Read Full Article)

   Bookmark or Share this article

   
   

   Related Articles

   • Framework and Resources for Natural Language Parser Evaluation
   • also published in arxiv.org
   • Clairlib Documentation v1.03
   • also published in arxiv.org

   • Entropy estimation of symbol sequences. (arXiv:cond-mat/0203436v1 [cond-mat.stat-mech] Cross Listed)
   • also published in arxiv.org

Login to comment.