Difference between revisions of "Minimum error rate training"
From Cohen Courses
Jump to navigationJump to search (Created page with 'Minimum error rate training (or MERT) is a [[Category::method]]. This is a work in progress by [[User::Fkeith|Francis Keith]] == Citation == MERT was originally proposed in the…') |
|||
| Line 1: | Line 1: | ||
| − | Minimum error rate training (or MERT) is a [[Category::method]]. This is a work in progress by [[User | + | Minimum error rate training (or MERT) is a [[Category::method]]. This is a work in progress by [[User:Fkeith|Francis Keith]] |
== Citation == | == 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 [http://acl.ldc.upenn.edu/acl2003/main/pdfs/Och.pdf) | 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 [http://acl.ldc.upenn.edu/acl2003/main/pdfs/Och.pdf) | ||
Revision as of 01:04, 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 [http://acl.ldc.upenn.edu/acl2003/main/pdfs/Och.pdf)
