International Workshop on Spoken Language Translation (IWSLT) 2007

Trento, Italy
October 15-16, 2007

Using Word Posterior Probabilities in Lattice Translation

Vicente Alabau, Alberto Sanchis, Francisco Casacuberta

Departament de Sistemes Informàtics i Computació, Institut Tecnològic d'Informàtica, Universitat Politècnica de València, Spain

In this paper we describe the statistical machine translation system developed at ITI/UPV, which aims especially at speech recognition and statistical machine translation integration, for the evaluation campaign of the International Workshop on Spoken Language Translation (2007).
   The system we have developed takes advantage of an improved word lattice representation that uses word posterior probabilities. These word posterior probabilities are then added as a feature to a log-linear model. This model includes a stochastic finite-state transducer which allows an easy lattice integration. Furthermore, it provides a statistical phrase-based reordering model that is able to perform local reorderings 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.

Full Paper     Presentation

Bibliographic reference.  Alabau, Vicente / Sanchis, Alberto / Casacuberta, Francisco (2007): "Using word posterior probabilities in lattice translation", In IWSLT-2007, 131-136.