Publication at Faculty of Mathematics and Physics |
2016
Abstract
This paper describes our submission to the Tuning Task of WMT16. We replace the grid search implemented as part of standard minimum-error rate training (MERT) in the Moses toolkit with a search based on particle swarm optimization (PSO).
An older variant of PSO has been previously successfully applied and we now test it in optimizing the Tuning Task model for English-to-Czech translation. We also adapt the method in some aspects to allow for even easier parallelization of the search.