Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction
Abstract
Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., linear chains) in which search and parameter estimation can be performed exactly. Unfortunately, in many complex problems, it is rare that exact search or parameter estimation is tractable. Instead of learning exact models and searching via heuristic means, we embrace this difficulty and treat the structured output problem in terms of approximate search. We present a framework for learning as search optimization, and two parameter updates with convergence the-orems and bounds. Empirical evidence shows that our integrated approach to learning and decoding can outperform exact models at smaller computational cost.
Cite
Text
Iii and Marcu. "Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction." International Conference on Machine Learning, 2005. doi:10.1145/1102351.1102373Markdown
[Iii and Marcu. "Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction." International Conference on Machine Learning, 2005.](https://mlanthology.org/icml/2005/iii2005icml-learning/) doi:10.1145/1102351.1102373BibTeX
@inproceedings{iii2005icml-learning,
title = {{Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction}},
author = {Iii, Hal Daumé and Marcu, Daniel},
booktitle = {International Conference on Machine Learning},
year = {2005},
pages = {169-176},
doi = {10.1145/1102351.1102373},
url = {https://mlanthology.org/icml/2005/iii2005icml-learning/}
}