import nltk
from nltk.corpus import udhr

english = udhr.raw('English-Latin1')
french = udhr.raw('French_Francais-Latin1')
italian = udhr.raw('Italian_Italiano-Latin1')
spanish = udhr.raw('Spanish_Espanol-Latin1')

english_train, english_dev = english[0:1000], english[1000:1100]
french_train, french_dev = french[0:1000], french[1000:1100]
italian_train, italian_dev = italian[0:1000], italian[1000:1100]
spanish_train, spanish_dev = spanish[0:1000], spanish[1000:1100]

english_test = udhr.words('English-Latin1')[0:1000]
french_test = udhr.words('French_Francais-Latin1')[0:1000]
italian_test = udhr.words('Italian_Italiano-Latin1')[0:1000]
spanish_test = udhr.words('Spanish_Espanol-Latin1')[0:1000]