def train(self, conll_path):
# pylint: disable=invalid-name
# pylint: disable=missing-docstring
eloss = 0.0
mloss = 0.0
eerrors = 0
etotal = 0
start = time.time()
shuffled_data = list(read_conll(conll_path))
random.shuffle(shuffled_data)
errs = []
lerrs = []
i_sentence = 0
for sentence in shuffled_data:
if i_sentence % 100 == 0 and i_sentence != 0:
print('Processing sentence number:', i_sentence, 'Loss:',
eloss / etotal, 'Errors:', (float(eerrors)) / etotal,
'Time',
time.time() - start)
start = time.time()
eerrors = 0
eloss = 0.0
etotal = 0
conll_sentence = [
entry for entry in sentence if isinstance(entry, ConllEntry)
]
for entry in conll_sentence:
c = float(self.words_count.get(entry.norm, 0))
drop_flag = (random.random() < (c / (0.25 + c)))
wordvec = self.wlookup[int(self.vocab.get(entry.norm, 0)) if drop_flag else 0] \
if self.wdims > 0 else None
posvec = self.plookup[int(
self.pos[entry.pos])] if self.pdims > 0 else None
entry.vec = concatenate(
[_f for _f in [wordvec, posvec, None] if _f])
entry.lstms = [entry.vec, entry.vec]
entry.headfov = None
entry.modfov = None
entry.rheadfov = None
entry.rmodfov = None
if self.blstm_flag:
lstm_forward = self.builders[0].initial_state()
lstm_backward = self.builders[1].initial_state()
for entry, rentry in zip(conll_sentence,
reversed(conll_sentence)):
lstm_forward = lstm_forward.add_input(entry.vec)
lstm_backward = lstm_backward.add_input(rentry.vec)
entry.lstms[1] = lstm_forward.output()
rentry.lstms[0] = lstm_backward.output()
if self.bibi_flag:
for entry in conll_sentence:
entry.vec = concatenate(entry.lstms)
blstm_forward = self.bbuilders[0].initial_state()
blstm_backward = self.bbuilders[1].initial_state()
for entry, rentry in zip(conll_sentence,
reversed(conll_sentence)):
blstm_forward = blstm_forward.add_input(entry.vec)
blstm_backward = blstm_backward.add_input(rentry.vec)
entry.lstms[1] = blstm_forward.output()
rentry.lstms[0] = blstm_backward.output()
scores, exprs = self._evaluate(conll_sentence)
gold = [entry.parent_id for entry in conll_sentence]
heads = decoder.parse_proj(scores,
gold if self.costaug_flag else None)
if self.labels_flag:
for modifier, head in enumerate(gold[1:]):
rscores, rexprs = self._evaluate_label(
conll_sentence, head, modifier + 1)
gold_label_ind = self.rels[conll_sentence[modifier +
1].relation]
wrong_label_ind = max(((label, scr)
for label, scr in enumerate(rscores)
if label != gold_label_ind),
key=itemgetter(1))[0]
if rscores[gold_label_ind] < rscores[wrong_label_ind] + 1:
lerrs.append(rexprs[wrong_label_ind] -
rexprs[gold_label_ind])
e = sum([1 for h, g in zip(heads[1:], gold[1:]) if h != g])
eerrors += e
if e > 0:
loss = [(exprs[h][i] - exprs[g][i])
for i, (h, g) in enumerate(zip(heads, gold))
if h != g] # * (1.0/float(e))
eloss += e
mloss += e
errs.extend(loss)
etotal += len(conll_sentence)
if i_sentence % 1 == 0 or errs > 0 or lerrs:
if errs or lerrs:
eerrs = (esum(errs + lerrs)) # * (1.0/(float(len(errs))))
eerrs.scalar_value()
eerrs.backward()
self.trainer.update()
errs = []
lerrs = []
renew_cg()
i_sentence += 1
if errs:
eerrs = (esum(errs + lerrs)) # * (1.0/(float(len(errs))))
eerrs.scalar_value()
eerrs.backward()
self.trainer.update()
renew_cg()
self.trainer.update()
print("Loss: ", mloss / i_sentence)
def train(self, conll_path):
# pylint: disable=invalid-name
# pylint: disable=missing-docstring
eloss = 0.0
mloss = 0.0
eerrors = 0
etotal = 0
start = time.time()
shuffled_data = list(read_conll(conll_path))
random.shuffle(shuffled_data)
errs = []
lerrs = []
i_sentence = 0
for sentence in shuffled_data:
if i_sentence % 100 == 0 and i_sentence != 0:
print('Processing sentence number:', i_sentence, 'Loss:',
eloss / etotal, 'Errors:',
(float(eerrors)) / etotal, 'Time', time.time() - start)
start = time.time()
eerrors = 0
eloss = 0.0
etotal = 0
conll_sentence = [entry for entry in sentence if isinstance(entry, ConllEntry)]
for entry in conll_sentence:
c = float(self.words_count.get(entry.norm, 0))
drop_flag = (random.random() < (c / (0.25 + c)))
wordvec = self.wlookup[int(self.vocab.get(entry.norm, 0)) if drop_flag else 0] \
if self.wdims > 0 else None
posvec = self.plookup[int(self.pos[entry.pos])] if self.pdims > 0 else None
entry.vec = concatenate([_f for _f in [wordvec, posvec, None] if _f])
entry.lstms = [entry.vec, entry.vec]
entry.headfov = None
entry.modfov = None
entry.rheadfov = None
entry.rmodfov = None
if self.blstm_flag:
lstm_forward = self.builders[0].initial_state()
lstm_backward = self.builders[1].initial_state()
for entry, rentry in zip(conll_sentence, reversed(conll_sentence)):
lstm_forward = lstm_forward.add_input(entry.vec)
lstm_backward = lstm_backward.add_input(rentry.vec)
entry.lstms[1] = lstm_forward.output()
rentry.lstms[0] = lstm_backward.output()
if self.bibi_flag:
for entry in conll_sentence:
entry.vec = concatenate(entry.lstms)
blstm_forward = self.bbuilders[0].initial_state()
blstm_backward = self.bbuilders[1].initial_state()
for entry, rentry in zip(conll_sentence, reversed(conll_sentence)):
blstm_forward = blstm_forward.add_input(entry.vec)
blstm_backward = blstm_backward.add_input(rentry.vec)
entry.lstms[1] = blstm_forward.output()
rentry.lstms[0] = blstm_backward.output()
scores, exprs = self._evaluate(conll_sentence)
gold = [entry.parent_id for entry in conll_sentence]
heads = decoder.parse_proj(scores, gold if self.costaug_flag else None)
if self.labels_flag:
for modifier, head in enumerate(gold[1:]):
rscores, rexprs = self._evaluate_label(conll_sentence, head, modifier + 1)
gold_label_ind = self.rels[conll_sentence[modifier + 1].relation]
wrong_label_ind = max(((label, scr) for label, scr in enumerate(rscores)
if label != gold_label_ind), key=itemgetter(1))[0]
if rscores[gold_label_ind] < rscores[wrong_label_ind] + 1:
lerrs.append(rexprs[wrong_label_ind] - rexprs[gold_label_ind])
e = sum([1 for h, g in zip(heads[1:], gold[1:]) if h != g])
eerrors += e
if e > 0:
loss = [(exprs[h][i] - exprs[g][i]) for i, (h, g) in
enumerate(zip(heads, gold)) if h != g] # * (1.0/float(e))
eloss += e
mloss += e
errs.extend(loss)
etotal += len(conll_sentence)
if i_sentence % 1 == 0 or errs > 0 or lerrs:
if errs or lerrs:
eerrs = (esum(errs + lerrs)) # * (1.0/(float(len(errs))))
eerrs.scalar_value()
eerrs.backward()
self.trainer.update()
errs = []
lerrs = []
renew_cg()
i_sentence += 1
if errs:
eerrs = (esum(errs + lerrs)) # * (1.0/(float(len(errs))))
eerrs.scalar_value()
eerrs.backward()
self.trainer.update()
renew_cg()
self.trainer.update()
print("Loss: ", mloss / i_sentence)
def predict(self, conll_path=None, conll=None):
# pylint: disable=missing-docstring
if conll is None:
conll = read_conll(conll_path)
for sentence in conll:
conll_sentence = [
entry for entry in sentence if isinstance(entry, ConllEntry)
]
for entry in conll_sentence:
wordvec = self.wlookup[int(self.vocab.get(
entry.norm, 0))] if self.wdims > 0 else None
posvec = self.plookup[int(
self.pos[entry.pos])] if self.pdims > 0 else None
entry.vec = concatenate(
[_f for _f in [wordvec, posvec, None] if _f])
entry.lstms = [entry.vec, entry.vec]
entry.headfov = None
entry.modfov = None
entry.rheadfov = None
entry.rmodfov = None
if self.blstm_flag:
lstm_forward = self.builders[0].initial_state()
lstm_backward = self.builders[1].initial_state()
for entry, rentry in zip(conll_sentence,
reversed(conll_sentence)):
lstm_forward = lstm_forward.add_input(entry.vec)
lstm_backward = lstm_backward.add_input(rentry.vec)
entry.lstms[1] = lstm_forward.output()
rentry.lstms[0] = lstm_backward.output()
if self.bibi_flag:
for entry in conll_sentence:
entry.vec = concatenate(entry.lstms)
blstm_forward = self.bbuilders[0].initial_state()
blstm_backward = self.bbuilders[1].initial_state()
for entry, rentry in zip(conll_sentence,
reversed(conll_sentence)):
blstm_forward = blstm_forward.add_input(entry.vec)
blstm_backward = blstm_backward.add_input(rentry.vec)
entry.lstms[1] = blstm_forward.output()
rentry.lstms[0] = blstm_backward.output()
scores, _ = self._evaluate(conll_sentence)
heads = decoder.parse_proj(scores)
for entry, head in zip(conll_sentence, heads):
entry.pred_parent_id = head
entry.pred_relation = '_'
dump = False
if self.labels_flag:
for modifier, head in enumerate(heads[1:]):
scores, _ = self._evaluate_label(conll_sentence, head,
modifier + 1)
conll_sentence[modifier + 1].pred_relation = \
self.irels[max(enumerate(scores), key=itemgetter(1))[0]]
renew_cg()
if not dump:
yield sentence
def predict(self, conll_path=None, conll=None):
# pylint: disable=missing-docstring
if conll is None:
conll = read_conll(conll_path)
for sentence in conll:
conll_sentence = [entry for entry in sentence if
isinstance(entry, ConllEntry)]
for entry in conll_sentence:
wordvec = self.wlookup[int(
self.vocab.get(entry.norm, 0))] if self.wdims > 0 else None
posvec = self.plookup[
int(self.pos[entry.pos])] if self.pdims > 0 else None
entry.vec = concatenate(
[_f for _f in [wordvec, posvec, None] if _f])
entry.lstms = [entry.vec, entry.vec]
entry.headfov = None
entry.modfov = None
entry.rheadfov = None
entry.rmodfov = None
if self.blstm_flag:
lstm_forward = self.builders[0].initial_state()
lstm_backward = self.builders[1].initial_state()
for entry, rentry in zip(conll_sentence, reversed(conll_sentence)):
lstm_forward = lstm_forward.add_input(entry.vec)
lstm_backward = lstm_backward.add_input(rentry.vec)
entry.lstms[1] = lstm_forward.output()
rentry.lstms[0] = lstm_backward.output()
if self.bibi_flag:
for entry in conll_sentence:
entry.vec = concatenate(entry.lstms)
blstm_forward = self.bbuilders[0].initial_state()
blstm_backward = self.bbuilders[1].initial_state()
for entry, rentry in zip(conll_sentence, reversed(conll_sentence)):
blstm_forward = blstm_forward.add_input(entry.vec)
blstm_backward = blstm_backward.add_input(rentry.vec)
entry.lstms[1] = blstm_forward.output()
rentry.lstms[0] = blstm_backward.output()
scores, _ = self._evaluate(conll_sentence)
heads = decoder.parse_proj(scores)
for entry, head in zip(conll_sentence, heads):
entry.pred_parent_id = head
entry.pred_relation = '_'
dump = False
if self.labels_flag:
for modifier, head in enumerate(heads[1:]):
scores, _ = self._evaluate_label(conll_sentence, head, modifier + 1)
conll_sentence[modifier + 1].pred_relation = \
self.irels[max(enumerate(scores), key=itemgetter(1))[0]]
renew_cg()
if not dump:
yield sentence
