Difference between revisions of "Minimum error rate training"
From Cohen Courses
Jump to navigationJump to search| Line 4: | Line 4: | ||
MERT was originally proposed in the paper [[RelatedPaper::Och ACL 2003|“Minimum Error Rate Training in Statistical Machine Translation”, Franz Josef Och, ACL, 2003, pp. 160-167.]] (found here [http://acl.ldc.upenn.edu/acl2003/main/pdfs/Och.pdf]) | MERT was originally proposed in the paper [[RelatedPaper::Och ACL 2003|“Minimum Error Rate Training in Statistical Machine Translation”, Franz Josef Och, ACL, 2003, pp. 160-167.]] (found here [http://acl.ldc.upenn.edu/acl2003/main/pdfs/Och.pdf]) | ||
| + | |||
| + | == Background == | ||
| + | |||
| + | When training a model, often times it is beneficial to take into account the actual evaluation method for that model. In many cases, training methods do not. MERT attempts to train models for [[AddressesProblem::Machine Translation|statistical machine translation]]. It attempts to optimize the parameters of the model while considering a more complex evaluation method than simply counting incorrect translations. It essentially attempts to train the model based on the method that will be used to evaluate the model. | ||
Revision as of 10:18, 13 November 2011
Minimum error rate training (or MERT) is a method. This is a work in progress by Francis Keith
Citation
MERT was originally proposed in the paper “Minimum Error Rate Training in Statistical Machine Translation”, Franz Josef Och, ACL, 2003, pp. 160-167. (found here [1])
Background
When training a model, often times it is beneficial to take into account the actual evaluation method for that model. In many cases, training methods do not. MERT attempts to train models for statistical machine translation. It attempts to optimize the parameters of the model while considering a more complex evaluation method than simply counting incorrect translations. It essentially attempts to train the model based on the method that will be used to evaluate the model.
