def __init__(self, n, alpha=None, ngram_model=None):
self.n = n
if ngram_model != None:
self.language_model = ngram_model
elif alpha != None:
self.language_model = NgramModel(n, alpha=alpha)
else:
self.language_model = NgramModel(n)
def __init__(self,
pronouncer=Pronouncer(),
phoneme_to_digit_dict=None,
max_word_length=None,
min_sentence_length=5,
n=3,
alpha=0.1,
select_most_likely=True,
tagger=UnigramTagger(brown.tagged_sents())):
'''
Initializes the NgramPOSContextEncoder. The encoder will consider the context of at most
(n - 1) previous words and choose the subsequent word with highest probability
part-of-speech and with highest n-gram probability if select_most_likely is True
(otherwise, will sample weighted by probabilities).
'''
super(NgramPOSContextEncoder,
self).__init__(pronouncer=pronouncer,
phoneme_to_digit_dict=phoneme_to_digit_dict,
max_word_length=max_word_length,
context_length=n - 1,
min_sentence_length=min_sentence_length)
self.ngram = NgramModel(n, alpha=alpha)
self.select_most_likely = select_most_likely
self.tagger = tagger
self.pos_ngram = NgramPOSModel(n, alpha=alpha)
def __init__(self,
pronouncer=Pronouncer(),
phoneme_to_digit_dict=None,
max_word_length=2):
'''
Initializes the UnigramGreedyEncoder. The encoder will greedily group digits to make words
as long as possible (where the length of a word refers to the number of digits it encodes).
'''
super(UnigramGreedyEncoder,
self).__init__(pronouncer=pronouncer,
phoneme_to_digit_dict=phoneme_to_digit_dict,
max_word_length=max_word_length)
self.unigram = NgramModel(1)
def __init__(self,
pronouncer=Pronouncer(),
phoneme_to_digit_dict=None,
max_word_length=None,
min_sentence_length=5,
n=3,
alpha=0.1,
select_most_likely=True,
tagger_type=UnigramTagger,
tagged_sents=brown.tagged_sents(tagset='universal'),
num_sentence_templates=100,
word_length_weight=10):
'''
Initializes the SentenceTaggerEncoder.
Uses the num_sentence_templates most common part-of-speech sentence types, requiring at
least min_sentence_length words per sentence. Favors words that encode more digits as a
function of word_length_weight (0 means unweighted). Scores words and sentences through an
n-gram model with the given n and alpha.
'''
super(SentenceTaggerEncoder,
self).__init__(pronouncer=pronouncer,
phoneme_to_digit_dict=phoneme_to_digit_dict,
max_word_length=max_word_length,
min_sentence_length=min_sentence_length,
n=n,
alpha=alpha,
select_most_likely=select_most_likely)
# set up our tagger and sentence_templates
self.tagger = tagger_type(tagged_sents)
self.tagged_sents = tagged_sents
self.num_sentence_templates = num_sentence_templates
# some parts of speech can be reasonably omitted from any sentence - we call these optional
self.optional_tags = ['DET', 'ADJ', 'ADV']
self.sentence_templates = self._get_sentence_templates()
self.word_length_weight = word_length_weight
# set up bigram model for post processing
self.bigram = NgramModel(n=2, alpha=0.05)