Abstract | ||
---|---|---|
The Microsoft Research translation system is a syntactically informed phrasal SMT system that uses a phrase translation model based on dependency treelets and a global reordering model based on the source dependency tree. These models are combined with several other knowledge sources in a log-linear manner. The weights of the individual components in the log-linear model are set by an automatic parameter-tuning method. We give a brief overview of the components of the system and discuss our experience with the Europarl data translating from English to Spanish. |
Year | Venue | Keywords |
---|---|---|
2006 | WMT@HLT-NAACL | europarl evaluation,phrasal smt system,global reordering model,log-linear model,automatic parameter-tuning method,microsoft research translation system,europarl data,dependency treelets,source dependency tree,log-linear manner,phrase translation model,microsoft research treelet translation |
Field | DocType | Citations |
Dependency tree,Computer science,Phrase,Natural language processing,Artificial intelligence | Conference | 4 |
PageRank | References | Authors |
0.69 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arul Menezes | 1 | 470 | 29.57 |
Kristina Toutanova | 2 | 3131 | 152.55 |
Chris Quirk | 3 | 70 | 4.97 |