Difference between revisions of "An End-to-End Discriminative Approach to Machine Translation"
| Line 7: | Line 7: | ||
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. | 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 === | + | === Translation Model === |
| + | The model used in this work is typically used in statatistical machine translation, where we view the translation task as a structured prediction problem, where each source segment is mapped to a target segment following a given model. In the case of MT, a hidden variable h is introduced which describes the sequence of derivations used to translate each source phrase in the source sentence s to a target phrase, leading to a translation t. Thus, we want to find the derivation h (hence the translation t) that maximizes the model's score: | ||
| + | |||
| + | <math> | ||
| + | f(x; w) = argmax_{t,h} w\dot \sigma(s,t,h) | ||
| + | </math> | ||
| + | |||
| + | === Perceptron-based Training === | ||
| + | The parameters w | ||
Revision as of 22:00, 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.
Translation Model
The model used in this work is typically used in statatistical machine translation, where we view the translation task as a structured prediction problem, where each source segment is mapped to a target segment following a given model. In the case of MT, a hidden variable h is introduced which describes the sequence of derivations used to translate each source phrase in the source sentence s to a target phrase, leading to a translation t. Thus, we want to find the derivation h (hence the translation t) that maximizes the model's score:
Perceptron-based Training
The parameters w
