Name
Abstract | ||
|---|---|---|
This is a description of the submissions made by the pattern recognition and human language technology group (PRHLT) of the Universitat Politècnica de València to the quality estimation task of the seventh workshop on statistical machine translation (WMT12). We focus on two different issues: how to effectively combine subsequence-level features into sentence-level features, and how to select the most adequate subset of features. Results showed that an adequate selection of a subset of highly discriminative features can improve efficiency and performance of the quality estimation system. |
Year | Venue | Keywords |
|---|---|---|
2012 | WMT@NAACL-HLT | discriminative feature,adequate selection,pattern recognition,universitat polit,different issue,prhlt submission,human language technology group,sentence-level feature,wmt12 quality estimation task,quality estimation task,quality estimation system,adequate subset |
Field | DocType | Citations |
Information retrieval,Computer science,Machine translation,Natural language processing,Artificial intelligence,Discriminative model,Language technology | Conference | 4 |
PageRank | References | Authors |
0.48 | 2 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jesús González Rubio | 1 | 4 | 0.48 |
| Alberto Sanchis | 2 | 73 | 7.67 |
| francisco casacuberta | 3 | 1439 | 161.33 |