SyMGiza++: A tool for parallel computation of symmetrized word alignment models

SyMGiza++ — a tool that computes symmetric word alignment models with the capability to take advantage of multi-processor systems — is presented. A series of fairly simple modifications to the original IBM/Giza++ word alignment models allows to update the symmetrized models between each iteration of the original training algorithms. We achieve a relative alignment quality improvement of more than 17% compared to Giza++ and MGiza++ on the standard Canadian Hansards task, while maintaining the speed improvements provided by MGiza++'s capability of parallel computations.