PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Kernel Regression Framework for SMT
Zhuoran Wang and John Shawe-Taylor
Machine Translation Volume 24, Number 2, pp. 87-102, 2010.

Abstract

This paper presents a novel regression framework to model both the translational equivalence problem and the parameter estimation problem in statistical machine translation (SMT). The proposed method kernelizes the training process by formulating the translation problem as a linear mapping among source and target word chunks (word n-grams of various length), which yields a regression problem with vector outputs. A kernel ridge regression model and a one-class classifier called maximum margin regression are explored for comparison, between which the former is proved to perform better in this task. The experimental results conceptually demonstrate its advantages of handling very high-dimensional features implicitly and flexibly. However, it shares the common drawback of kernel methods, i.e. the lack of scalability. For real-world application, a more practical solution based on locally linear regression hyperplane approximation is proposed by using online relevant training examples subsetting. In addition, we also introduce a novel way to integrate language models into this particular machine translation framework, which utilizes the language model as a penalty item in the objective function of the regression model, since its n-gram representation exactly matches the definition of our feature space.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:6958
Deposited By:Zhuoran Wang
Deposited On:20 June 2010