Publication at Faculty of Mathematics and Physics |
2010
Abstract
The paper describes our experiments with English-Czech machine translation for WMT10 in 2010. Focusing primarily on the translation to Czech, our additions to the standard Moses phrase-based MT pipeline include two-step translation to overcome target-side data sparseness and optimization towards SemPOS, a metric better suited for evaluating Czech.
Unfortunately, none of the approaches bring a significant improvement over our standard setup.