def build_lattice(self, pt, sentence):
'''
Gets a phrase table and the tokenized sentence and outputs a lattice
file formatted as follows:
whole sentence
1-1:
<English translation> <Translation score>
<English translation> <Translation score>
...
1-2:
<English translation> <Translation score>
<English translation> <Translation score>
...
2-2:
The spans n-n refer to the tokens of the input Spanish sentence
'''
sentence = tokenize(sentence)
self.sentence = sentence
for start in xrange(len(sentence)):
self.phrases[start] = {}
for end in xrange(start+1, len(sentence)+1):
foreign = sentence[start:end]
p = Phrase(foreign, start, end)
if len(foreign) == 1 and foreign[0] == ',':
p.translations = [Translation(foreign, (',',), 0)]
else:
p.translations = pt.translate(foreign)
self.phrases[start][end] = p
def create_initial(cls):
initial_phrase = Phrase(None, None, None)
initial_phrase.translations = [Translation(None, (u'<s>',), 0)]
return cls(None, initial_phrase, 0, (u'<s>',))