Name
Abstract | ||
|---|---|---|
In this paper we describe the statistical machine transla- tion system developed at ITI/UPV, which aims especially at speech recognition and statistical machine translation in- tegration, for the evaluation campaign of the Internationa l Workshop on Spoken Language Translation (2007). The system we have developed takes advantage of an im- proved word lattice representation that uses word posterior probabilities. These word posterior probabilities are the n added as a feature to a log-linear model. This model includes a stochastic finite-state transducer which allows an easy la t- tice integration. Furthermore, it provides a statistical p hrase- based reordering model that is able to perform local reorder- ings of the output. We have tested this model on the Italian-English corpus, for clean text, 1-best ASR and lattice ASR inputs. The results and conclusions of such experiments are reported at the end of this paper. |
Year | Venue | Keywords |
|---|---|---|
2007 | IWSLT | speech recognition,log linear model,finite state transducer,posterior probability |
Field | DocType | Citations |
Rule-based machine translation,Spoken language translation,Cache language model,Lattice (order),Computer science,Word error rate,Machine translation,Machine translation system,Speech recognition,Posterior probability,Artificial intelligence,Natural language processing | Conference | 1 |
PageRank | References | Authors |
0.37 | 17 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Vicente Alabau | 1 | 8 | 2.61 |
| Alberto Sanchis | 2 | 73 | 7.67 |
| francisco casacuberta | 3 | 1439 | 161.33 |
| Departament de Sistemes | 4 | 2 | 0.72 |