Name
Abstract | ||
|---|---|---|
Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this
paper, two length models along with two parameter estimation methods for statistical machine translation (SMT) are presented.
More precisely, we incorporate explicit length modelling in a state-of-the-art log-linear SMT system as an additional feature
function in order to prove the contribution of length information. Finally, promising experimental results are reported on
a reference SMT task.
|
Year | DOI | Venue |
|---|---|---|
2011 | 10.1016/j.patcog.2012.01.006 | Pattern Recognition |
Keywords | DocType | Volume |
alternative parametrisations,statistical machine translation,reference smt task,explicit length,additional feature function,length information,explicit bilingual length,statistical pattern recognition,length model,explicit length modelling,state-of-the-art log-linear smt system,log linear models | Conference | 45 |
Issue | ISSN | Citations |
9 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 22 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Joan Albert Silvestre-Cerdà | 1 | 7 | 2.15 |
| Jesús Andrés-Ferrer | 2 | 73 | 7.52 |
| Jorge Civera | 3 | 243 | 27.87 |