Zhuoran Wang and John Shawe-Taylor
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- chapter
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.003.0009
- Subject:
- Computer Science, Machine Learning
This chapter presents a novel framework for machine translation based on kernel ridge regression. As a kernel method, the framework has the advantage of capturing the correspondences among the ...
More
This chapter presents a novel framework for machine translation based on kernel ridge regression. As a kernel method, the framework has the advantage of capturing the correspondences among the features of inputs and outputs in a very high-dimensional space. But the drawback is that its computational complexities are much higher than probabilistic models. A solution is sparse approximation, which poses the problem of extracting a sufficient amount of relevant bilingual training samples for a given input. Other essential improvements to this model could be the integration of additional language models and the utilization of linguistic knowledge.Less
This chapter presents a novel framework for machine translation based on kernel ridge regression. As a kernel method, the framework has the advantage of capturing the correspondences among the features of inputs and outputs in a very high-dimensional space. But the drawback is that its computational complexities are much higher than probabilistic models. A solution is sparse approximation, which poses the problem of extracting a sufficient amount of relevant bilingual training samples for a given input. Other essential improvements to this model could be the integration of additional language models and the utilization of linguistic knowledge.
