emb = args.wordemb.lower()
print('Word Embedding: ', emb)
if emb == 'glove':
emb_file = '../../../../data/embedding/glove.6B.100d.txt'
else:
emb_file = None
char_emb_file = args.charemb.lower()
print('Char Embedding: ', char_emb_file)
name = 'BaseLSTM' # catnlp
config = Config()
config.layers = 2
config.optim = 'Adam'
config.char_features = 'CNN'
config.lr = 0.015
config.hidden_dim = 200
config.bid_flag = True
config.number_normalized = True
data_initialization(config, train_file, dev_file, test_file)
config.gpu = gpu
config.word_features = name
print('Word features: ', config.word_features)
config.generate_instance(train_file, 'train')
config.generate_instance(dev_file, 'dev')
config.generate_instance(test_file, 'test')
if emb_file:
print('load word emb file...norm: ', config.norm_word_emb)
config.build_word_pretain_emb(emb_file)
if char_emb_file != 'none':
print('load char emb file...norm: ', config.norm_char_emb)
config.build_char_pretrain_emb(char_emb_file)
if emb == 'glove':
emb_file = '../../../data/embedding/glove.6B.100d.txt'
elif emb == 'glove300d':
emb_file = '../../../data/embedding/glove.840B.300d.txt'
else:
emb_file = None
char_emb_file = args.charemb.lower()
print('Char Embedding: ', char_emb_file)
name = 'LSTM' # catnlp
config = Config()
config.layers = 2
config.optim = 'Adam'
config.char_features = 'CNN'
config.word_emb_dim = 300
config.hidden_dim = 600
config.bid_flag = True
config.number_normalized = True
data_initialization(config, train_file, dev_file, test_file)
config.gpu = gpu
config.word_features = name
print('Word features: ', config.word_features)
config.generate_instance(train_file, 'train')
config.generate_instance(dev_file, 'dev')
config.generate_instance(test_file, 'test')
if emb_file:
print('load word emb file...norm: ', config.norm_word_emb)
config.build_word_pretain_emb(emb_file)
if char_emb_file != 'none':
print('load char emb file...norm: ', config.norm_char_emb)
config.build_char_pretrain_emb(char_emb_file)
