Using word posterior probabilities in lattice translation

Vicente Alabau, Alberto Sanchis, Francisco Casacuberta


Abstract
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.
Anthology ID:
2007.iwslt-1.19
Volume:
Proceedings of the Fourth International Workshop on Spoken Language Translation
Month:
October 15-16
Year:
2007
Address:
Trento, Italy
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2007.iwslt-1.19
DOI:
Bibkey:
Cite (ACL):
Vicente Alabau, Alberto Sanchis, and Francisco Casacuberta. 2007. Using word posterior probabilities in lattice translation. In Proceedings of the Fourth International Workshop on Spoken Language Translation, Trento, Italy.
Cite (Informal):
Using word posterior probabilities in lattice translation (Alabau et al., IWSLT 2007)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2007.iwslt-1.19.pdf