Loading...
Please wait, while we are loading the content...
Similar Documents
Batch tuning strategies for statistical machine translation (2012)
| Content Provider | CiteSeerX |
|---|---|
| Author | Cherry, Colin Foster, George |
| Description | In Proc. of NAACL |
| Abstract | There has been a proliferation of recent work on SMT tuning algorithms capable of handling larger feature sets than the traditional MERT approach. We analyze a number of these algorithms in terms of their sentencelevel loss functions, which motivates several new approaches, including a Structured SVM. We perform empirical comparisons of eight different tuning strategies, including MERT, in a variety of settings. Among other results, we find that a simple and efficient batch version of MIRA performs at least as well as training online, and consistently outperforms other options. 1 |
| File Format | |
| Publisher Date | 2012-01-01 |
| Access Restriction | Open |
| Subject Keyword | Feature Set Recent Work Sentencelevel Loss Function Several New Approach Statistical Machine Translation Structured Svm Training Online Efficient Batch Version Traditional Mert Approach Mira Performs Empirical Comparison |
| Content Type | Text |
