Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
courses:rg:transductive_learning_for_statistical_machine_translation [2010/12/08 21:34] jawaid |
courses:rg:transductive_learning_for_statistical_machine_translation [2010/12/08 21:49] jawaid |
||
---|---|---|---|
Line 17: | Line 17: | ||
===== Comments ===== | ===== Comments ===== | ||
- | * The Paper very well describes the transductive learning algorithm, **Algorithm 1** which is inspired by Yarowsky algorithm [1]. | + | |
* In algorithm 1, the translation model is estimated based on the sentence pairs in bilingual data L. Then a set of source language sentences, U, is translated based on the current model. A subset of good transaltions and their sources, Ti, is selected on each iteration and added to the training data. These sentence pairs are replaces in each iteration and only the original data, L, is fixed throughout algorithm. | * In algorithm 1, the translation model is estimated based on the sentence pairs in bilingual data L. Then a set of source language sentences, U, is translated based on the current model. A subset of good transaltions and their sources, Ti, is selected on each iteration and added to the training data. These sentence pairs are replaces in each iteration and only the original data, L, is fixed throughout algorithm. | ||
Line 23: | Line 23: | ||
* Algorithm 1 is based on **Estimate**, | * Algorithm 1 is based on **Estimate**, | ||
- | * Estimate function estimates the model parameters. The authors used three different model for parameters estimation. **Full Re-training**, | + | * Estimate function estimates the model parameters |
* Scoring function assign a score to each translation t. The scoring functions used in the paper are: **Length-normalized Score** and **Confidence Estimation**. | * Scoring function assign a score to each translation t. The scoring functions used in the paper are: **Length-normalized Score** and **Confidence Estimation**. | ||
* Selection function is used to create additional training data Ti which is used in next iteration i+1 by **Estimate** to augment the original bilingual data. The selection functions used in this paper are: **Importance Sampling**, **Selection using a Threshold** and **Keep All**. | * Selection function is used to create additional training data Ti which is used in next iteration i+1 by **Estimate** to augment the original bilingual data. The selection functions used in this paper are: **Importance Sampling**, **Selection using a Threshold** and **Keep All**. | ||
+ | |||
+ | * Data filtering is performed on both bilingual and monolingual data to keep only that part of the data which is relevant to the test data. | ||
| |