Name
Abstract | ||
|---|---|---|
We present a machine translation framework based on Kernel Regression techniques. The translation process is modeled as a string-to-string mapping. For doing so, first both source and target strings are mapped to a natural vector space obtaining feature vectors. Afterwards, a translation mapping is defined from the source feature vector to the target feature vector. This translation mapping is learnt by linear regression. Once the target feature vector is obtained, we use a multi-graph search to find all the possible target strings whose mappings correspond to the "translated" feature vector. We present experiments in a small but relevant task showing encouraging results. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-02172-5_51 | IbPRIA |
Keywords | Field | DocType |
possible target string,machine translation,kernel regression approach,target feature vector,natural vector space,target string,source feature vector,translation mapping,machine translation framework,translation process,feature vector,string-to-string mapping,vector space,linear regression,kernel regression | Graph kernel,Feature vector,Pattern recognition,Computer science,Machine translation,Feature (machine learning),Polynomial kernel,Artificial intelligence,Relevance vector machine,Kernel method,String kernel | Conference |
Volume | ISSN | Citations |
5524 | 0302-9743 | 7 |
PageRank | References | Authors |
0.58 | 13 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nicolás Serrano | 1 | 277 | 32.84 |
| Jesús Andrés-Ferrer | 2 | 73 | 7.52 |
| francisco casacuberta | 3 | 1439 | 161.33 |