... Dan Klein. 2010. Discriminative mod-eling of extraction setsfor machine translation. In Pro-ceedings of the 48th AnnualMeeting of the Association for Computational Linguistics, pages 1453–1463.John ... training reg-imen up to Model 4, and combine alignmentswith grow-diag-final-and. For the proposedmodels, we train for 100 iterations, and use the finalsample acquired at the end of the training ... training process for our experiments using a single sample6. In addition,6 For most models, while likelihood continued to increasegradually for all 100 iterations, BLEU score gains plateaued...