def substitute(self, text):
results = []
tokens = self.tokenizer(text)
pos = nltk.pos_tag(tokens)
aug_idxes = self._get_aug_idxes(pos)
if aug_idxes is None:
return text
for i, token in enumerate(tokens):
# Skip if no augment for word
if i not in aug_idxes:
results.append(token)
continue
word_poses = PartOfSpeech.pos2wn(pos[i][1])
synets = []
if word_poses is None or len(word_poses) == 0:
# Use every possible words as the mapping does not defined correctly
synets.extend(self.model.synsets(pos[i][0], lang=self.lang))
else:
for word_pos in word_poses:
synets.extend(
self.model.synsets(pos[i][0],
pos=word_pos,
lang=self.lang))
augmented_data = []
for synet in synets:
candidates = []
for lema in synet.lemmas():
if self.synonyms:
candidates.append(lema.name())
else:
if lema.antonyms():
candidates.append(lema.antonyms()[0].name())
for candidate in candidates:
if candidate.lower() != token.lower():
augmented_data.append(candidate)
if len(augmented_data) == 0:
results.append(token)
else:
candidate = self.sample(augmented_data, 1)[0]
candidate = candidate.replace("_", " ").replace("-",
" ").lower()
results.append(self.align_capitalization(token, candidate))
return self.reverse_tokenizer(results)
def substitute(self, text):
results = []
tokens = self.tokenizer(text)
pos = nltk.pos_tag(tokens)
aug_cnt = self.generate_aug_cnt(len(tokens))
word_idxes = [i for i, t in enumerate(tokens)]
word_idxes = self.skip_aug(word_idxes, pos)
aug_idexes = self.sample(word_idxes, aug_cnt)
for i, token in enumerate(tokens):
# Skip if no augment for word
if i not in aug_idexes:
results.append(token)
continue
word_poses = PartOfSpeech.pos2wn(pos[i][1])
synets = []
if word_poses is None or len(word_poses) == 0:
# Use every possible words as the mapping does not defined correctly
synets.extend(self.model.synsets(pos[i][0]))
else:
for word_pos in word_poses:
synets.extend(self.model.synsets(pos[i][0], pos=word_pos))
augmented_data = []
for synet in synets:
for candidate in synet.lemma_names():
if candidate.lower() != token.lower():
augmented_data.append(candidate)
if len(augmented_data) == 0:
results.append(token)
else:
candidate = self.sample(augmented_data, 1)[0]
results.append(self.align_capitalization(token, candidate))
return self.reverse_tokenizer(results)
def substitute(self, data):
results = []
tokens = self.tokenizer(data)
pos = self.model.pos_tag(tokens)
aug_idxes = self._get_aug_idxes(pos)
if aug_idxes is None:
return data
for i, token in enumerate(tokens):
# Skip if no augment for word
if i not in aug_idxes:
results.append(token)
continue
word_poses = PartOfSpeech.pos2wn(pos[i][1])
candidates = []
if word_poses is None or len(word_poses) == 0:
# Use every possible words as the mapping does not defined correctly
candidates.extend(self.model.predict(pos[i][0]))
else:
for word_pos in word_poses:
candidates.extend(
self.model.predict(pos[i][0], pos=word_pos))
candidates = [c for c in candidates if c.lower() != token.lower()]
if len(candidates) == 0:
results.append(token)
else:
candidate = self.sample(candidates, 1)[0]
candidate = candidate.replace("_", " ").replace("-",
" ").lower()
results.append(self.align_capitalization(token, candidate))
return self.reverse_tokenizer(results)
