def test_trellis_score():
global nb_weights, hmm_trans_weights, tag_to_ix, all_tags, vocab, word_to_ix
sentence = "they can can fish".split()
initial_vec = np.full((1, len(all_tags)), -np.inf)
initial_vec[0][
tag_to_ix[START_TAG]] = 0 #setting all the score to START_TAG
prev_scores = torch.autograd.Variable(
torch.from_numpy(initial_vec.astype(np.float32)))
emission_probs, tag_transition_probs = hmm.compute_weights_variables(nb_weights, hmm_trans_weights,\
vocab, word_to_ix, tag_to_ix)
path_score, best_path = viterbi.build_trellis(
all_tags, tag_to_ix, [emission_probs[word_to_ix[w]] for w in sentence],
tag_transition_probs)
eq_(path_score.data.numpy(), -17)
sentence = "they can can can can fish".split()
path_score, best_path = viterbi.build_trellis(
all_tags, tag_to_ix, [emission_probs[word_to_ix[w]] for w in sentence],
tag_transition_probs)
eq_(path_score.data.numpy(), -25.)
def predict(self, sentence):
"""
This function predicts the tags by using the viterbi algorithm. You should be calling the viterbi algorithm from here.
Inputs:
- feats: the hidden state scores for each token in the input sentence.
Consider this to be the emission potential of each token for each tag.
- gold_tags: the gold sequence of tags
:returns:
- the best_path which is a sequence of tags
"""
lstm_feats = self.forward(sentence).view(len(sentence), -1)
all_tags = [tag for tag, value in self.tag_to_ix.items()]
score, path = viterbi.build_trellis(all_tags, self.tag_to_ix,
lstm_feats, self.transitions)
return path
def test_hmm_on_example_sentence():
global nb_weights, hmm_trans_weights, all_tags
tag_to_ix={}
for tag in list(all_tags):
tag_to_ix[tag]=len(tag_to_ix)
vocab, word_to_ix = most_common.get_word_to_ix(TRAIN_FILE)
emission_probs, tag_transition_probs = hmm.compute_weights_variables(nb_weights, hmm_trans_weights, \
vocab, word_to_ix, tag_to_ix)
score, pred_tags = viterbi.build_trellis(all_tags,
tag_to_ix,
[emission_probs[word_to_ix[w]] for w in ['they', 'can', 'can', 'fish','.']],
tag_transition_probs)
assert_almost_equal(score.data.numpy()[0],-32.4456, places=2)
eq_(pred_tags,['PRON', 'AUX', 'AUX', 'NOUN','PUNCT'])
def test_hmm_on_example_sentence():
global nb_weights, hmm_trans_weights, all_tags
tag_to_ix = {}
for tag in list(all_tags):
tag_to_ix[tag] = len(tag_to_ix)
vocab, word_to_ix = most_common.get_word_to_ix(TRAIN_FILE)
emission_probs, tag_transition_probs = hmm.compute_weights_variables(nb_weights, hmm_trans_weights, \
vocab, word_to_ix, tag_to_ix)
score, pred_tags = viterbi.build_trellis(all_tags, tag_to_ix, [
emission_probs[word_to_ix[w]]
for w in ['they', 'can', 'can', 'fish', '.']
], tag_transition_probs)
assert_almost_equal(score.data.numpy()[0], -32.4456, places=2)
eq_(pred_tags, ['PRON', 'AUX', 'AUX', 'NOUN', 'PUNCT'])
def test_build_trellis():
global hand_weights
sentence = "they can can fish".split()
all_tags = ['NOUN','VERB']
# modify the hand weights so you can't read off the answer to 3.1 :)
hand_weights['NOUN','they',EMIT] = -2
hand_weights['VERB','fish',EMIT] = -5
hand_weights['VERB','VERB',TRANS] = -2
trellis = viterbi.build_trellis(sentence,hmm.hmm_features,hand_weights,all_tags)
eq_(len(trellis),4)
eq_(len(trellis[-1]),2)
eq_(trellis[-1]['VERB'],(-18,'VERB'))
eq_(trellis[-2]['NOUN'],(-11,'VERB'))
eq_(trellis[1]['VERB'],(-7,'NOUN'))
eq_(trellis[1]['NOUN'],(-11,'NOUN'))
def test_build_trellis():
global hand_weights
sentence = "they can can fish".split()
all_tags = ['NOUN', 'VERB']
# modify the hand weights so you can't read off the answer to 3.1 :)
hand_weights['NOUN', 'they', EMIT] = -2
hand_weights['VERB', 'fish', EMIT] = -5
hand_weights['VERB', 'VERB', TRANS] = -2
trellis = viterbi.build_trellis(sentence, hmm.hmm_features, hand_weights,
all_tags)
eq_(len(trellis), 4)
eq_(len(trellis[-1]), 2)
eq_(trellis[-1]['VERB'], (-18, 'VERB'))
eq_(trellis[-2]['NOUN'], (-11, 'VERB'))
eq_(trellis[1]['VERB'], (-7, 'NOUN'))
eq_(trellis[1]['NOUN'], (-11, 'NOUN'))