L1 Regularized Regression for Reranking and System Combination in Machine Translation
BibTeX
@MISC{Biçici_l1regularized,
author = {Ergun Biçici and Deniz Yuret},
title = {L1 Regularized Regression for Reranking and System Combination in Machine Translation},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We use L1 regularized transductive regression to learn mappings between source and target features of the training sets derived for each test sentence and use these mappings to rerank translation outputs. We compare the effectiveness of L1 regularization techniques for regression to learn mappings between features given in a sparse feature matrix. The results show the effectiveness of using L1 regularization versus L2 used in ridge regression. We show that regression mapping is effective in reranking translation outputs and in selecting the best system combinations with encouraging results on different language pairs. 1
Citations
| 1089 | Atomic decomposition by basis pursuit - Chen, Donoho, et al. - 1998 |
| 998 | Regression shrinkage and selection via the lasso - Tibshirani - 1996 |
| 519 | Kernel Methods for Pattern Analysis - Shawe-Taylor, Cristianini - 2004 |
| 434 | Moses: Open source toolkit for statistical machine translation - Koehn, Hoang, et al. - 2007 |
| 12 | Transductive learning for statistical machine translation - Ueffing, Haffari, et al. - 2007 |
| 10 | An empirical study on computing consensus translations from multiple machine translation systems - Macherey, Och - 2007 |
| 8 | Forward stagewise regression and the monotone lasso - Hastie, Taylor, et al. - 2007 |
| 8 | Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics - Human |
| 2 | Multiplicative updates for the lasso - Mørup, Clemmensen - 2007 |
