def main():
english = tokenize("data/100ktok.low.en")
spanish = tokenize("data/100ktok.low.es")
training_set, held_out_set, test_set = get_datasets(english, spanish)
translations = get_word_translations("100000_trans.txt")
search = BeamSearch(training_set, held_out_set, translations)
print search.translate(test_set[8])
def main():
english = tokenize("data/100ktok.low.en")
spanish = tokenize("data/100ktok.low.es")
training_set, test_set, translated_set = get_datasets(english, spanish)
translations = get_word_translations("3000_trans.txt")
print "Original Sentence:", ' '.join(test_set[0])
translator = DirectTrans(translations)
print "Direct Translation:", ' '.join(translator.translate(test_set[0]))
test_output = open('trans_beam.txt','w')
true_output = open('trans_true.txt','w')
search = BeamSearch(training_set, translations)
print "Beam Translation:", ' '.join(search.translate(test_set[0]))
print "True Translation:", ' '.join(translated_set[0])
def main():
english = tokenize("data/100ktok.low.en")
spanish = tokenize("data/100ktok.low.es")
training_set, test_set, translated_set = get_datasets(english, spanish)
translations = get_word_translations("3000_trans.txt")
search = BeamSearch(training_set, translations)
test_output = open('trans_beam.txt','w')
true_output = open('trans_true.txt','w')
for i in range(len(test_set)):
print "Translating sentence", i, "..."
test_output.write(' '.join(search.translate(test_set[i])) + "\n")
true_output.write(' '.join(translated_set[i]) + "\n")
test_output.close()
true_output.close()