Difference between revisions of "An End-to-End Discriminative Approach to Machine Translation"
From Cohen Courses
Jump to navigationJump to search| Line 5: | Line 5: | ||
=== Summary === | === Summary === | ||
| − | In this work, a discriminative approach to learn a translation model from parallel sentences. The translation task is viewed as the problem of finding the derivation h that mazimizes the translation score from the source s and target t. This score is calculated as a weighted feature combination, which is one of the main contributions of this paper. Another major contribution is the parameter training method which is performed using a weighted perceptron algorithm. | + | In this work, a discriminative approach to learn a translation model from parallel sentences. The translation task is viewed as the problem of finding the derivation h that mazimizes the translation score from the source s and target t. This score is calculated as a weighted feature combination, which is one of the main contributions of this paper. Another major contribution is the parameter training method which is performed using a weighted perceptron algorithm. In this aspect, the paper shows that updating parameters locally so that no radical changes are made to the current translation in each step performs better than radically changing the translation to correspond to the reference, in each update. |
| + | |||
| + | === Translation === | ||
Revision as of 21:51, 5 November 2012
Citation
Summary
In this work, a discriminative approach to learn a translation model from parallel sentences. The translation task is viewed as the problem of finding the derivation h that mazimizes the translation score from the source s and target t. This score is calculated as a weighted feature combination, which is one of the main contributions of this paper. Another major contribution is the parameter training method which is performed using a weighted perceptron algorithm. In this aspect, the paper shows that updating parameters locally so that no radical changes are made to the current translation in each step performs better than radically changing the translation to correspond to the reference, in each update.
