Difference between revisions of "An End-to-End Discriminative Approach to Machine Translation"
From Cohen Courses
Jump to navigationJump to searchLine 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 this paper | + | 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. |
Revision as of 21:47, 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.