... 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 ... number of words in each corpus for TM andLM training, tuning, and testing.7.1 Experimental SetupThe data for French, German, and Spanish are fromthe 2010 Workshop on Statistical Machine Transla-tion ... 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...