February 21, 2010

L1 Regularization for Learning Word Alignments in Sparse Feature Matrices

Ergun Bicici and Deniz Yuret. 1st CSE Student Workshop (CSW’10), 21 February 2010, Koc Istinye Campus, Istanbul. (PDF, Poster)

Sparse feature representations can be used in various domains. We compare the effectiveness of $L_1$ regularization techniques for regression to learn mappings between features given in a sparse feature matrix. We apply these techniques for learning word alignments commonly used for machine translation. The performance of the learned mappings are measured using the phrase table generated on a larger corpus by a state of the art word aligner. The results show the effectiveness of using $L_1$ regularization versus $L_2$ used in ridge regression.

Related link

No comments: