Sciweavers

1053 search results - page 14 / 211
» Learning Rules to Improve a Machine Translation System
Sort
View
EMNLP
2009
13 years 5 months ago
Synchronous Tree Adjoining Machine Translation
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
Steve DeNeefe, Kevin Knight
ACL
2009
13 years 5 months ago
Improving Tree-to-Tree Translation with Packed Forests
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...
Yang Liu, Yajuan Lü, Qun Liu
ACL
2003
13 years 8 months ago
Feedback Cleaning of Machine Translation Rules Using Automatic Evaluation
When rules of transfer-based machine translation (MT) are automatically acquired from bilingual corpora, incorrect/redundant rules are generated due to acquisition errors or trans...
Kenji Imamura, Eiichiro Sumita, Yuji Matsumoto
EACL
2003
ACL Anthology
13 years 8 months ago
Automatic Construction of Machine Translation Knowledge Using Translation Literalness
When machine translation (MT) knowledge is automatically constructed from bilingual corpora, redundant rules are acquired due to translation variety. These rules increase ambiguit...
Kenji Imamura, Eiichiro Sumita, Yuji Matsumoto