def build_dataloader(token_features,
labels,
batch_size,
missing_tagspace,
corpus_mask_value,
tag2idx,
chr2idx,
token2idx,
caseless,
shuffle=False,
drop_last=False):
dataset, forw_dev, back_dev = utils.construct_bucket_mean_vb_wc(
token_features, labels, missing_tagspace, tag2idx, chr2idx, token2idx,
caseless, corpus_mask_value)
dataloader = [
torch.utils.data.DataLoader(tup,
batch_size,
shuffle=shuffle,
drop_last=drop_last) for tup in dataset
]
return dataloader
ALLOW_SPANLEN = checkpoint_file['ALLOW_SPANLEN']
with codecs.open(args.dev_file, 'r', 'utf-8') as f:
dev_lines = f.readlines()
with codecs.open(args.test_file, 'r', 'utf-8') as f:
test_lines = f.readlines()
dev_features, dev_labels = utils.read_corpus(dev_lines)
test_features, test_labels = utils.read_corpus(test_lines)
dev_dataset = utils.construct_bucket_mean_vb_wc(
dev_features,
dev_labels,
CRF_l_map,
SCRF_l_map,
c_map,
f_map,
SCRF_stop_tag=SCRF_l_map['<STOP>'],
train_set=False)
test_dataset = utils.construct_bucket_mean_vb_wc(
test_features,
test_labels,
CRF_l_map,
SCRF_l_map,
c_map,
f_map,
SCRF_stop_tag=SCRF_l_map['<STOP>'],
train_set=False)
dev_dataset_loader = [
c_thresholds=args.mini_count,
if_shrink_w_feature=False)
f_set = {v for v in f_map}
f_map = utils.shrink_features(f_map, train_features, args.mini_count)
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_features), f_set)
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_features), dt_f_set)
f_map, embedding_tensor, in_doc_words = utils.load_embedding(args.emb_file, ' ', f_map, dt_f_set, args.unk, args.word_embedding_dim, shrink_to_corpus=args.shrink_embedding)
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_labels))
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_labels), l_set)
print('constructing dataset')
dataset, dataset_onlycrf = utils.construct_bucket_mean_vb_wc(train_features, train_labels, CRF_l_map, SCRF_l_map, c_map, f_map, SCRF_stop_tag=SCRF_l_map['<STOP>'], ALLOW_SPANLEN=args.allowspan, train_set=True)
dev_dataset = utils.construct_bucket_mean_vb_wc(dev_features, dev_labels, CRF_l_map, SCRF_l_map, c_map, f_map, SCRF_stop_tag=SCRF_l_map['<STOP>'], train_set=False)
test_dataset = utils.construct_bucket_mean_vb_wc(test_features, test_labels, CRF_l_map, SCRF_l_map, c_map, f_map, SCRF_stop_tag=SCRF_l_map['<STOP>'], train_set=False)
dataset_loader = [torch.utils.data.DataLoader(tup, args.batch_size, shuffle=True, drop_last=False) for tup in dataset]
dataset_loader_crf = [torch.utils.data.DataLoader(tup, 3, shuffle=True, drop_last=False) for tup in dataset_onlycrf] if dataset_onlycrf else None
dev_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in dev_dataset]
test_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in test_dataset]
print('building model')
model = ner_model(args.word_embedding_dim, args.word_hidden_dim, args.word_lstm_layers, len(f_map),
len(c_map), args.char_embedding_dim, args.char_lstm_hidden_dim, args.cnn_filter_num,
args.char_lstm_layers, args.char_lstm, args.dropout_ratio, args.high_way, args.highway_layers,
CRF_l_map['<start>'], CRF_l_map['<pad>'], len(CRF_l_map), SCRF_l_map, args.scrf_dense_dim,
in_doc_words,args.index_embeds_dim, args.allowspan, SCRF_l_map['<START>'], SCRF_l_map['<STOP>'], args.grconv)
torch.cuda.set_device(args.gpu)
# load corpus
if args.test_file:
with codecs.open(args.test_file, 'r', 'utf-8') as f:
test_lines = f.readlines()
else:
with codecs.open(jd['test_file'], 'r', 'utf-8') as f:
test_lines = f.readlines()
# converting format
test_features, test_labels = utils.read_corpus(test_lines)
# construct dataset
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(
test_features, test_labels, l_map, c_map, f_map, jd['caseless'])
test_dataset_loader = [
torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False)
for tup in test_dataset
]
# build model
ner_model = LM_LSTM_CRF(len(l_map),
len(c_map),
jd['char_dim'],
jd['char_hidden'],
jd['char_layers'],
jd['word_dim'],
jd['word_hidden'],
jd['word_layers'],
dt_f_set,
args.caseless,
args.unk,
args.word_dim,
shrink_to_corpus=args.shrink_embedding)
print("embedding size: '{}'".format(len(f_map)))
for label in l_set:
if label not in l_map:
l_map[label] = len(l_map)
print('constructing dataset')
for i in range(file_num):
# construct dataset
dataset, forw_corp, back_corp = utils.construct_bucket_mean_vb_wc(
train_features[i], train_labels[i], l_map, char_map, f_map,
args.caseless)
dev_dataset, forw_dev, back_dev = utils.construct_bucket_mean_vb_wc(
dev_features[i], dev_labels[i], l_map, char_map, f_map,
args.caseless)
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(
test_features[i], test_labels[i], l_map, char_map, f_map,
args.caseless)
dataset_loader.append([
torch.utils.data.DataLoader(tup,
args.batch_size,
shuffle=True,
drop_last=False) for tup in dataset
])
dev_dataset_loader.append([
print("feature size: '{}'".format(len(f_map)))
print('loading embedding')
if args.fine_tune: # which means does not do fine-tune
f_map = {'<eof>': 0}
f_map, embedding_tensor, in_doc_words = utils.load_embedding_wlm(args.emb_file, ' ', f_map, dt_f_set, args.caseless, args.unk, args.word_dim, shrink_to_corpus=args.shrink_embedding)
print("embedding size: '{}'".format(len(f_map)))
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_labels))
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_labels), l_set)
for label in l_set:
if label not in l_map:
l_map[label] = len(l_map)
print('constructing dataset')
# construct dataset
dataset, forw_corp, back_corp = utils.construct_bucket_mean_vb_wc(train_features, train_labels, l_map, c_map, f_map, args.caseless)
dev_dataset, forw_dev, back_dev = utils.construct_bucket_mean_vb_wc(dev_features, dev_labels, l_map, c_map, f_map, args.caseless)
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(test_features, test_labels, l_map, c_map, f_map, args.caseless)
dataset_loader = [torch.utils.data.DataLoader(tup, args.batch_size, shuffle=True, drop_last=False) for tup in dataset]
dev_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in dev_dataset]
test_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in test_dataset]
# build model
print('building model')
ner_model = LM_LSTM_CRF(len(l_map), len(c_map), args.char_dim, args.char_hidden, args.char_layers, args.word_dim, args.word_hidden, args.word_layers, len(f_map), args.drop_out, large_CRF=args.small_crf, if_highway=args.high_way, in_doc_words=in_doc_words, highway_layers = args.highway_layers)
if args.load_check_point:
ner_model.load_state_dict(checkpoint_file['state_dict'])
else:
if not args.rand_embedding:
c_map = checkpoint_file['c_map']
in_doc_words = checkpoint_file['in_doc_words']
SCRF_l_map = checkpoint_file['SCRF_l_map']
ALLOW_SPANLEN = checkpoint_file['ALLOW_SPANLEN']
with codecs.open(args.dev_file, 'r', 'utf-8') as f:
dev_lines = f.readlines()
with codecs.open(args.test_file, 'r', 'utf-8') as f:
test_lines = f.readlines()
dev_features, dev_labels = utils.read_corpus(dev_lines)
test_features, test_labels = utils.read_corpus(test_lines)
dev_dataset = utils.construct_bucket_mean_vb_wc(dev_features, dev_labels, CRF_l_map, SCRF_l_map, c_map, f_map, SCRF_stop_tag=SCRF_l_map['<STOP>'], train_set=False)
test_dataset = utils.construct_bucket_mean_vb_wc(test_features, test_labels, CRF_l_map, SCRF_l_map, c_map, f_map, SCRF_stop_tag=SCRF_l_map['<STOP>'], train_set=False)
dev_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in dev_dataset]
test_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in test_dataset]
print('build model')
model = ner_model(jd['word_embedding_dim'], jd['word_hidden_dim'], jd['word_lstm_layers'],
len(f_map), len(c_map), jd['char_embedding_dim'], jd['char_lstm_hidden_dim'],
jd['cnn_filter_num'], jd['char_lstm_layers'], jd['char_lstm'],jd['dropout_ratio'],
jd['high_way'], jd['highway_layers'], CRF_l_map['<start>'], CRF_l_map['<pad>'],
len(CRF_l_map), SCRF_l_map, jd['scrf_dense_dim'], in_doc_words,
jd['index_embeds_dim'], jd['allowspan'], SCRF_l_map['<START>'], SCRF_l_map['<STOP>'],
jd['grconv'])
print('load model')
f_map = {'<eof>': 0}
f_map, embedding_tensor, in_doc_words = utils.load_embedding_wlm(args.emb_file, ' ', f_map, dt_f_set, args.caseless, args.unk, args.word_dim, shrink_to_corpus=args.shrink_embedding)
print("embedding size: '{}'".format(len(f_map)))
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_labels))
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_labels), l_set)
for label in l_set:
if label not in l_map:
l_map[label] = len(l_map)
print('constructing dataset')
# construct dataset
dataset, forw_corp, back_corp = utils.construct_bucket_mean_vb_wc(train_features, train_labels, l_map, c_map, f_map, args.caseless)
dev_dataset, forw_dev, back_dev = utils.construct_bucket_mean_vb_wc(dev_features, dev_labels, l_map, c_map, f_map, args.caseless)
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(test_features, test_labels, l_map, c_map, f_map, args.caseless)
co_dataset,_,_=utils.construct_bucket_mean_vb_wc(co_features,co_labels,l_map,c_map,f_map,args.caseless)
dataset_loader = [torch.utils.data.DataLoader(tup, args.batch_size, shuffle=True, drop_last=False) for tup in dataset]
dev_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in dev_dataset]
test_dataset_loader = [torch.utils.data.DataLoader(tup, 1, shuffle=False, drop_last=False) for tup in test_dataset]
co_dataset_loader=[torch.utils.data.DataLoader(tup,args.batch_size,shuffle=True,drop_last=False) for tup in co_dataset]
#string match part
word_to_id,emb_tensor,emb =utils.string_match_embedding(args.emb_file,args.word_dim)
# build model
print('building model')
def read_dataset(self, file_dict, dataset_name, *args, **kwargs):
print('loading corpus')
self.file_num = len(self.args.train_file)
for i in range(self.file_num):
with codecs.open(self.args.train_file[i], 'r', 'utf-8') as f:
lines0 = f.readlines()
lines0 = lines0[0:2000]
# print (len(lines0))
self.lines.append(lines0)
for i in range(self.file_num):
with codecs.open(self.args.dev_file[i], 'r', 'utf-8') as f:
dev_lines0 = f.readlines()
dev_lines0 = dev_lines0[0:2000]
self.dev_lines.append(dev_lines0)
for i in range(self.file_num):
with codecs.open(self.args.test_file[i], 'r', 'utf-8') as f:
test_lines0 = f.readlines()
test_lines0 = test_lines0[0:2000]
self.test_lines.append(test_lines0)
for i in range(self.file_num):
dev_features0, dev_labels0 = utils.read_corpus(self.dev_lines[i])
test_features0, test_labels0 = utils.read_corpus(
self.test_lines[i])
self.dev_features.append(dev_features0)
self.test_features.append(test_features0)
self.dev_labels.append(dev_labels0)
self.test_labels.append(test_labels0)
if self.args.output_annotation: # NEW
test_word0, test_word_tag0 = utils.read_features(
self.test_lines[i])
self.test_word.append(test_word0)
self.test_word_tag.append(test_word_tag0)
#print (len(self.test_word), len(self.test_labels))
if self.args.load_check_point:
if os.path.isfile(self.args.load_check_point):
print("loading checkpoint: '{}'".format(
self.args.load_check_point))
self.checkpoint_file = torch.load(
self.args.load_check_point)
self.args.start_epoch = self.checkpoint_file['epoch']
self.f_map = self.checkpoint_file['f_map']
self.l_map = self.checkpoint_file['l_map']
c_map = self.checkpoint_file['c_map']
self.in_doc_words = self.checkpoint_file['in_doc_words']
self.train_features, self.train_labels = utils.read_corpus(
self.lines[i])
else:
print("no checkpoint found at: '{}'".format(
self.args.load_check_point))
else:
print('constructing coding table')
train_features0, train_labels0, self.f_map, self.l_map, self.char_count = utils.generate_corpus_char(
self.lines[i],
self.f_map,
self.l_map,
self.char_count,
c_thresholds=self.args.mini_count,
if_shrink_w_feature=False)
self.train_features.append(train_features0)
self.train_labels.append(train_labels0)
self.train_features_tot += train_features0
shrink_char_count = [
k for (k, v) in iter(self.char_count.items())
if v >= self.args.mini_count
]
self.char_map = {
shrink_char_count[ind]: ind
for ind in range(0, len(shrink_char_count))
}
self.char_map['<u>'] = len(self.char_map) # unk for char
self.char_map[' '] = len(self.char_map) # concat for char
self.char_map['\n'] = len(self.char_map) # eof for char
f_set = {v for v in self.f_map}
dt_f_set = f_set
self.f_map = utils.shrink_features(self.f_map, self.train_features_tot,
self.args.mini_count)
l_set = set()
for i in range(self.file_num):
dt_f_set = functools.reduce(
lambda x, y: x | y, map(lambda t: set(t),
self.dev_features[i]), dt_f_set)
dt_f_set = functools.reduce(
lambda x, y: x | y, map(lambda t: set(t),
self.test_features[i]), dt_f_set)
l_set = functools.reduce(lambda x, y: x | y,
map(lambda t: set(t), self.dev_labels[i]),
l_set)
l_set = functools.reduce(
lambda x, y: x | y, map(lambda t: set(t), self.test_labels[i]),
l_set)
if not self.args.rand_embedding:
print("feature size: '{}'".format(len(self.f_map)))
print('loading embedding')
if self.args.fine_tune: # which means does not do fine-tune
self.f_map = {'<eof>': 0}
self.f_map, self.embedding_tensor, self.in_doc_words = utils.load_embedding_wlm(
self.args.emb_file,
' ',
self.f_map,
dt_f_set,
self.args.caseless,
self.args.unk,
self.args.word_dim,
shrink_to_corpus=self.args.shrink_embedding)
print("embedding size: '{}'".format(len(self.f_map)))
for label in l_set:
if label not in self.l_map:
self.l_map[label] = len(self.l_map)
print('constructing dataset')
for i in range(self.file_num):
# construct dataset
dataset, forw_corp, back_corp = utils.construct_bucket_mean_vb_wc(
self.train_features[i], self.train_labels[i], self.l_map,
self.char_map, self.f_map, self.args.caseless)
dev_dataset, forw_dev, back_dev = utils.construct_bucket_mean_vb_wc(
self.dev_features[i], self.dev_labels[i], self.l_map,
self.char_map, self.f_map, self.args.caseless)
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(
self.test_features[i], self.test_labels[i], self.l_map,
self.char_map, self.f_map, self.args.caseless)
self.dataset_loader.append([
torch.utils.data.DataLoader(tup,
self.args.batch_size,
shuffle=True,
drop_last=False) for tup in dataset
])
self.dev_dataset_loader.append([
torch.utils.data.DataLoader(tup,
50,
shuffle=False,
drop_last=False)
for tup in dev_dataset
])
self.test_dataset_loader.append([
torch.utils.data.DataLoader(tup,
50,
shuffle=False,
drop_last=False)
for tup in test_dataset
])
# load corpus
if args.test_file:
with codecs.open(args.test_file, 'r', 'utf-8') as f:
test_lines = f.readlines()
else:
with codecs.open(jd['test_file'], 'r', 'utf-8') as f:
test_lines = f.readlines()
# converting format
test_features, test_labels = utils.read_corpus(test_lines)
# construct dataset
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(test_features, test_labels, l_map, c_map, f_map, jd['caseless'])
test_dataset_loader = [torch.utils.data.DataLoader(tup, 50, shuffle=False, drop_last=False) for tup in test_dataset]
# build model
ner_model = LM_LSTM_CRF(len(l_map), len(c_map), jd['char_dim'], jd['char_hidden'], jd['char_layers'], jd['word_dim'], jd['word_hidden'], jd['word_layers'], len(f_map), jd['drop_out'], large_CRF=jd['small_crf'], if_highway=jd['high_way'], in_doc_words=in_doc_words, highway_layers = jd['highway_layers'])
ner_model.load_state_dict(checkpoint_file['state_dict'])
if args.gpu >= 0:
if_cuda = True
torch.cuda.set_device(args.gpu)
ner_model.cuda()
packer = CRFRepack_WC(len(l_map), True)
else:
if_cuda = False
