def evaluate_recurrent(self, word_inds, tag_inds, test=False):
fwd1 = self.fwd_lstm1.initial_state()
back1 = self.back_lstm1.initial_state()
fwd2 = self.fwd_lstm2.initial_state()
back2 = self.back_lstm2.initial_state()
sentence = []
for (w, t) in zip(word_inds, tag_inds):
wordvec = pycnn.lookup(self.model['word-embed'], w)
tagvec = pycnn.lookup(self.model['tag-embed'], t)
vec = pycnn.concatenate([wordvec, tagvec])
sentence.append(vec)
fwd1_out = []
for vec in sentence:
fwd1 = fwd1.add_input(vec)
fwd_vec = fwd1.output()
fwd1_out.append(fwd_vec)
back1_out = []
for vec in reversed(sentence):
back1 = back1.add_input(vec)
back_vec = back1.output()
back1_out.append(back_vec)
lstm2_input = []
for (f, b) in zip(fwd1_out, reversed(back1_out)):
lstm2_input.append(pycnn.concatenate([f, b]))
fwd2_out = []
for vec in lstm2_input:
if self.droprate > 0 and not test:
vec = pycnn.dropout(vec, self.droprate)
fwd2 = fwd2.add_input(vec)
fwd_vec = fwd2.output()
fwd2_out.append(fwd_vec)
back2_out = []
for vec in reversed(lstm2_input):
if self.droprate > 0 and not test:
vec = pycnn.dropout(vec, self.droprate)
back2 = back2.add_input(vec)
back_vec = back2.output()
back2_out.append(back_vec)
fwd_out = [
pycnn.concatenate([f1, f2])
for (f1, f2) in zip(fwd1_out, fwd2_out)
]
back_out = [
pycnn.concatenate([b1, b2])
for (b1, b2) in zip(back1_out, back2_out)
]
return fwd_out, back_out[::-1]
def _get_char_representation(self, word):
word_char_vectors = []
for char in word.text:
char_index = self.char_indexer.get_index(char)
if char_index is None:
print "Warning: Unexpected char '%s' (word='%s')" % (char, word.text)
continue
char_vector = lookup(self.model["char_lookup"], char_index)
word_char_vectors.append(char_vector)
lstm_forward = self.char_builders[0].initial_state()
lstm_backward = self.char_builders[1].initial_state()
for char_vector, reverse_char_vector in zip(word_char_vectors, reversed(word_char_vectors)):
lstm_forward = lstm_forward.add_input(char_vector)
lstm_backward = lstm_backward.add_input(reverse_char_vector)
return concatenate([lstm_forward.output(), lstm_backward.output()])
def build_tagging_graph(word_indices, model, builder):
"""
build the computational graph
:param word_indices: list of indices
:param model: current model to access parameters
:param builder: builder to create state combinations
:return: forward and backward sequence
"""
pycnn.renew_cg()
f_init = builder.initial_state()
# retrieve embeddings from the model and add noise
word_embeddings = [pycnn.lookup(model["word_lookup"], w) for w in word_indices]
word_embeddings = [pycnn.noise(we, args.noise) for we in word_embeddings]
# compute the expressions for the forward pass
forward_sequence = [x.output() for x in f_init.add_inputs(word_embeddings)]
return forward_sequence
def _get_char_representation(self, word, use_dropout):
word_char_vectors = []
for char in word.text:
char_index = self.char_indexer.get_index(char)
if char_index is None:
print "Warning: Unexpected char '%s' (word='%s')" % (char,
word.text)
continue
char_vector = lookup(self.model["char_lookup"], char_index)
word_char_vectors.append(char_vector)
lstm_forward = self.char_builders[0].initial_state()
lstm_backward = self.char_builders[1].initial_state()
for char_vector, reverse_char_vector in zip(
word_char_vectors, reversed(word_char_vectors)):
lstm_forward = lstm_forward.add_input(char_vector)
lstm_backward = lstm_backward.add_input(reverse_char_vector)
return concatenate([lstm_forward.output(), lstm_backward.output()])
def build_tagging_graph(words, model, builders):
"""
build the computational graph
:param words: list of indices
:param model: current model to access parameters
:param builders: builder to create state combinations
:return: forward and backward sequence
"""
pycnn.renew_cg()
f_init, b_init = [b.initial_state() for b in builders]
# retrieve embeddings from the model and add noise
word_embeddings = [pycnn.lookup(model["lookup"], w) for w in words]
word_embeddings = [pycnn.noise(we, 0.1) for we in word_embeddings]
# compute the expressions for the forward and backward pass
forward_sequence = [x.output() for x in f_init.add_inputs(word_embeddings)]
backward_sequence = [x.output() for x in b_init.add_inputs(reversed(word_embeddings))]
return list(zip(forward_sequence, reversed(backward_sequence)))
if args.target in ['joint']:
pOutAge = model.add_parameters("OUT_AGE", (num_labels, MLP_HIDDEN_LAYER_SIZE))
biasOutAge = model.add_parameters("BIAS_OUT_AGE", (num_labels))
elif args.target in ['age', 'both']:
pOutAge = model.add_parameters("OUT_AGE", (len(age_labels), MLP_HIDDEN_LAYER_SIZE))
biasOutAge = model.add_parameters("BIAS_OUT_AGE", (len(age_labels)))
if args.target in ['gender', 'both']:
pOutGender = model.add_parameters("OUT2", (len(gender_labels), MLP_HIDDEN_LAYER_SIZE))
biasOutGender = model.add_parameters("BIAS_OUT2", (len(gender_labels)))
print("declared variables", file=sys.stderr)
pycnn.renew_cg()
new_word_embeddings = [pycnn.lookup(model["word_lookup"], w) for w in train[0][0][0]]
print(new_word_embeddings)
pycnn.conv1d_narrow(new_word_embeddings, pycnn.cg())
sys.exit()
def build_tagging_graph(word_indices, model, builder):
"""
build the computational graph
:param word_indices: list of indices
:param model: current model to access parameters
:param builder: builder to create state combinations
:return: forward and backward sequence
"""
def _get_word_embedding(self, word):
word_index = self.word_indexer.get_index(word.text.lower()) or self._unk_word_index
return lookup(self.model["word_lookup"], word_index)
def _get_word_embedding(self, word, use_dropout):
word_index = self.word_indexer.get_index(
word.text.lower()) or self._unk_word_index
if use_dropout and random.random() < 0.5:
word_index = self._unk_word_index
return lookup(self.model["word_lookup"], word_index)
def _get_word_embedding(self, word):
word_index = self.word_indexer.get_index(
word.text.lower()) or self._unk_word_index
return lookup(self.model["word_lookup"], word_index)
def _get_word_embedding(self, word, use_dropout):
word_index = self.word_indexer.get_index(word.text.lower()) or self._unk_word_index
if use_dropout and random.random() < 0.5:
word_index = self._unk_word_index
return lookup(self.model["word_lookup"], word_index)