def __call__(self, config):
random.seed(1)
np.random.seed(1)
torch.manual_seed(1)
#self.distance = F.cosine_similarity
self.succeed_number = 0
corpus, loader = self.pre_attack(config)
print(self.vocab.char_dict)
self.punct_rel_idx = self.vocab.rel_dict[CONSTANT.PUNCT]
self.punct_idx = [value for key, value in self.vocab.char_dict.items() if not (key.isdigit() or key.isalpha())]
# for saving
attack_corpus = Corpus([])
self.embedding_weight = self.parser.char_lstm.embed.weight
self.parser.char_lstm.embed.register_backward_hook(self.char_embed_backward_hook)
# attack seq generator
# self.attack_seq_generator = self.get_attack_seq_generator(config)
self.attack(loader, config, attack_corpus)
# save to file
if config.save_result_to_file:
attack_corpus_save_path = self.get_attack_corpus_saving_path(config)
attack_corpus.save(attack_corpus_save_path)
print('Result after attacking has saved in {}'.format(attack_corpus_save_path))
def __call__(self, config):
random.seed(1)
np.random.seed(1)
torch.manual_seed(1)
self.init_config(config)
corpus, loader = self.pre_attack(config)
self.parser.eval()
attack_corpus = Corpus([])
# attack seq generator
self.attack_seq_generator = self.get_attack_seq_generator(config)
#self.attack_index = AttackIndexUnkReplacement(config, self.vocab, self.parser)
with torch.no_grad():
self.attack(config, loader, corpus, attack_corpus)
if config.save_result_to_file:
# corpus_save_path = '{}/{}'.format(config.result_path,'origin.conllx')
# corpus.save(corpus_save_path)
# print('Result before attacking has saved in {}'.format(corpus_save_path))
attack_corpus_save_path = self.get_attack_corpus_saving_path(
config)
attack_corpus.save(attack_corpus_save_path)
print('Result after attacking has saved in {}'.format(
attack_corpus_save_path))
def __call__(self, config):
random.seed(1)
np.random.seed(1)
torch.manual_seed(1)
corpus, loader = self.pre_attack(config)
# for saving
attack_corpus = Corpus([])
# attack seq generator
self.attack_seq_generator = self.get_attack_seq_generator(config)
self.attack(loader, config, attack_corpus)
# save to file
if config.save_result_to_file:
attack_corpus_save_path = self.get_attack_corpus_saving_path(config)
attack_corpus.save(attack_corpus_save_path)
print('Result after attacking has saved in {}'.format(attack_corpus_save_path))
def __call__(self, config):
self.vocab = torch.load(config.vocab)
self.parser = load_parser(fetch_best_ckpt_name(config.parser_model))
self.task = ParserTask(self.vocab, self.parser)
# load training data
corpus = Corpus.load(config.ftrain)
dataset = TextDataset(self.vocab.numericalize(corpus, training=True))
loader = DataLoader(dataset=dataset, collate_fn=collate_fn)
augmentation_corpus = Corpus([])
training_data_number = len(corpus.sentences)
self.attack_seq_generator = self.get_attack_seq_generator(config)
# random prob to decide whether to change a specific training data
# if prob[index] < augmentation_rate, augmented.
prob = np.random.uniform(0.0, 1.0, size=(training_data_number,))
for index, (seq_idx, tag_idx, chars, arcs, rels) in enumerate(loader):
sentence = corpus.sentences[index]
augmentation_corpus.sentences.append(sentence)
if index % 1000 == 0:
print("{} sentences have processed! ".format(index))
if prob[index] < config.augmentation_rate:
seqs = self.get_seqs_name(seq_idx)
tags = self.get_tags_name(tag_idx)
mask = self.get_mask(seq_idx, self.vocab.pad_index, punct_list=self.vocab.puncts)
raw_metric = self.task.evaluate([(seq_idx, tag_idx, chars, arcs, rels)],mst=config.mst)
augmentation_seq, _, _, _, _, _ = self.attack_seq_generator.generate_attack_seq(' '.join(seqs[1:]), seq_idx, tags, tag_idx, chars, arcs, rels, mask, raw_metric)
augmentation_corpus.sentences.append(init_sentence(sentence.FORM, tuple(augmentation_seq[1:]), sentence.POS, sentence.HEAD, sentence.DEPREL))
if config.input == 'char':
saved_file = '{}/ptb_train_typo_only_substitute_{:.0f}%_{}.sd'.format(config.augmentation_dir, config.augmentation_rate*100, config.revised_rate)
else:
saved_file = '{}/ptb_train_{:.0f}%_{}.sd'.format(config.augmentation_dir, config.augmentation_rate*100, config.revised_rate)
print("Complete! {} sentences have processed!".format(training_data_number))
print("Current training data number is {}.".format(len(augmentation_corpus.sentences)))
print("The augmentation data are saved to file {}".format(saved_file))
augmentation_corpus.save(saved_file)