Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
courses:rg:transductive_learning_for_statistical_machine_translation [2010/12/08 22:00] jawaid |
courses:rg:transductive_learning_for_statistical_machine_translation [2010/12/08 23:35] (current) jawaid |
||
|---|---|---|---|
| Line 4: | Line 4: | ||
| ===== Introduction ===== | ===== Introduction ===== | ||
| - | |||
| The paper is about the use of transductive semi-supervised methods for the effective use of monolingual data from the source language in order to improve translation quality. Transductive means that they repeatedly translate sentences from the development set or test set and use generated translation to improve the SMT system. Transductive learning is another mean to adapt the SMT system to a new type of text. | The paper is about the use of transductive semi-supervised methods for the effective use of monolingual data from the source language in order to improve translation quality. Transductive means that they repeatedly translate sentences from the development set or test set and use generated translation to improve the SMT system. Transductive learning is another mean to adapt the SMT system to a new type of text. | ||
| Line 17: | Line 16: | ||
| ===== Comments ===== | ===== Comments ===== | ||
| - | * The Paper very well describes the transductive learning algorithm, **Algorithm 1** which is inspired by Yarowsky algorithm [1]. | + | * The Paper very well describes the transductive learning algorithm, **Algorithm 1** which is inspired by Yarowsky algorithm [1][2]. |
| * 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 31: | Line 30: | ||
| * 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. | * 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. | ||
| - | * They used three different evaluation metrics for evaluating translation | + | * They used three different evaluation metrics for evaluating translation |
| - | * | + | * Experiments are performed on EuroParl and NIST corpus. On EuroParl corpus the selection and scoring was carried out using importance sampling with normalized score. Three different experiments are performed on the Europarl corpus which didn't produce significant improvement in the accuracy on output translation. Experiments on NIST data are performed using three different test sets where the output translation of each test set yield the best score when threshold-based selection method was combined with confidence estimation as scoring method. |
| + | * The main issue with this paper is that number of iterations that are selected to train the model are not described. And according to Figure 1 in the paper, graph achieves global maximum on iteration 16 and iteration 18 on train100k and train150K corpus. Where our main concern is they might know the BLEU score from the test set they already have and they stopped the training process or cut down the graph after particular iteration where BLEU is optimized according to already computed BLEU score. | ||
| + | * Adding examples in the paper on which improvement is achieved would have helped much better to understand the impact of this training scheme. | ||
| + | |||
| + | * Ambiguous terminology is used for defining the feasibility setting in Table 3. ' | ||
| ===== Suggested Additional Reading ===== | ===== Suggested Additional Reading ===== | ||
| * [1] D. Yarowsky. 1995. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. In Proc. ACL | * [1] D. Yarowsky. 1995. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. In Proc. ACL | ||
| - | * [2] | + | * [2] S. Abney. 2004. Understanding the Yarowsky Algorithm. Comput. Ling., 30(3). |
| ===== What do we like about the paper ===== | ===== What do we like about the paper ===== | ||
| + | * Even if the reader doesn' | ||
| ===== What do we dislike about the paper ===== | ===== What do we dislike about the paper ===== | ||
| - | * The technique defined | + | * The semi supervised learning scheme presented |
| - | + | Comments by Bushra Jawaid | |