def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_char_emb = True
self.norm_word_emb = False
self.char_alphabet = Alphabet('character')
self.label_alphabet = Alphabet('label', True)
self.word_dict = Word_Trie()
self.word_alphabet = Alphabet('word')
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.char_emb_dim = 50
self.word_emb_dim = 50
self.pretrain_char_embedding = None
self.pretrain_word_embedding = None
self.label_size = 0
def __init__(self):
self.max_sentence_length = 200
self.number_normalized = True
self.norm_char_emb = True
self.norm_gaz_emb = True
self.dataset_name = 'msra'
self.tagscheme = "NoSeg"
self.char_alphabet = Alphabet('character')
self.label_alphabet = Alphabet('label', unkflag=False)
self.gaz_lower = False
self.gaz = Gazetteer(self.gaz_lower)
self.gaz_alphabet = Alphabet('gaz')
self.train_ids = []
self.dev_ids = []
self.test_ids = []
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.char_emb_dim = 100
self.gaz_emb_dim = 100
self.pretrain_char_embedding = None
self.pretrain_gaz_embedding = None
self.dev_cut_num = 0
self.train_cut_num = 0
self.test_cut_num = 0
self.cut_num = 0
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_word_emb = True
self.norm_gaz_emb = False
self.use_single = True
self.word_alphabet = Alphabet('word')
self.label_alphabet = Alphabet('label', True)
self.gaz_lower = False
self.gaz = Gazetteer(self.gaz_lower, self.use_single)
self.gaz_alphabet = Alphabet('gaz')
self.HP_fix_gaz_emb = False
self.HP_use_gaz = True
self.tagScheme = "NoSeg"
self.char_features = "LSTM"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.train_golds = []
self.dev_golds = []
self.test_golds = []
self.raw_golds = []
self.word_emb_dim = 50
self.gaz_emb_dim = 100
self.gaz_dropout = 0.3
self.pretrain_word_embedding = None
self.pretrain_gaz_embedding = None
self.label_size = 0
self.word_alphabet_size = 0
self.label_alphabet_size = 0
### hyperparameters
self.HP_iteration = 100
self.HP_batch_size = 10
self.HP_hidden_dim = 100
self.HP_dropout = 0.3
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_gpu = False
self.HP_lr = 0.015
self.HP_lr_decay = 0.05
self.HP_clip = 5.0
self.HP_momentum = 0
self.gpu = False
self.enty_dropout = 0.3
# self.cls_mode = 'sigmoid' # or softmax
self.cls_mode = 'softmax'
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_word_emb = True
self.norm_biword_emb = True
self.norm_gaz_emb = False
self.word_alphabet = Alphabet('word')
self.biword_alphabet = Alphabet('biword')
# self.char_alphabet = Alphabet('character')
self.label_alphabet = Alphabet('label', True)
self.gaz_lower = False
self.gaz = Gazetteer(self.gaz_lower)
self.gaz_alphabet = Alphabet('gaz')
self.gaz_count = {}
self.gaz_split = {}
self.biword_count = {}
self.HP_fix_gaz_emb = False
self.HP_use_gaz = True
self.HP_use_count = False
self.tagScheme = "NoSeg"
self.char_features = "LSTM"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.train_split_index = []
self.dev_split_index = []
self.use_bigram = True
self.word_emb_dim = 50
self.biword_emb_dim = 50
# self.char_emb_dim = 30
self.gaz_emb_dim = 50
# self.gaz_dropout = 0.5
self.pretrain_word_embedding = None
self.pretrain_biword_embedding = None
self.pretrain_gaz_embedding = None
self.label_size = 0
self.word_alphabet_size = 0
self.biword_alphabet_size = 0
# self.char_alphabet_size = 0
self.label_alphabet_size = 0
def __init__(self):
self.relational_alphabet = Alphabet("Relation",
unkflag=False,
padflag=False)
self.train_data = None
self.valid_data = None
self.test_data = None
def initial_feature_alphabets(self):
items = open(self.train_dir, 'r').readline().strip('\n').split()
print(items)
total_column = len(items)
if total_column > 2:
for idx in range(1, total_column - 1):
feature_prefix = items[idx].split(']', 1)[0] + "]"
print("feature_prefix:{}".format(feature_prefix))
self.feature_alphabets.append(Alphabet(feature_prefix))
self.feature_name.append(feature_prefix)
print("Find feature: ", feature_prefix)
self.feature_num = len(self.feature_alphabets)
self.pretrain_feature_embeddings = [None] * self.feature_num
self.feature_emb_dims = [20] * self.feature_num
self.feature_emb_dirs = [None] * self.feature_num
self.norm_feature_embs = [False] * self.feature_num
self.feature_alphabet_sizes = [0] * self.feature_num
if self.feat_config:
for idx in range(self.feature_num):
if self.feature_name[idx] in self.feat_config:
self.feature_emb_dims[idx] = self.feat_config[
self.feature_name[idx]]['emb_size']
self.feature_emb_dirs[idx] = self.feat_config[
self.feature_name[idx]]['emb_dir']
self.norm_feature_embs[idx] = self.feat_config[
self.feature_name[idx]]['emb_norm']
def __init__(self):
self.relational_alphabet = Alphabet("Relation",
unkflag=False,
padflag=False)
self.train_loader = []
self.valid_loader = []
self.test_loader = []
self.weight = {}
def __init__(self, data_config_file, alphabet_path, if_train=True):
if if_train:
with open(data_config_file, 'r') as rf:
self.data_config = yaml.load(rf, Loader=yaml.FullLoader)
# init data file
mode = self.data_config['mode']
self.data_file = os.path.join(ROOT_PATH,
self.data_config['data'][mode])
# init ac tree
specific_words_file = os.path.join(
ROOT_PATH, self.data_config['specific_words_file'])
self.trees = Trees.build_trees(specific_words_file)
# init alphabet
self.char_alphabet = Alphabet('char')
self.intent_alphabet = Alphabet('intent')
self.label_alphabet = Alphabet('label', label=True)
self.char_alphabet_size, self.intent_alphabet_size, self.label_alphabet_size = -1, -1, -1
# pad length
self.char_max_length = self.data_config['char_max_length']
# read data file
with open(self.data_file, 'r') as rf:
self.corpus = rf.readlines()
self.build_alphabet(alphabet_path)
self.texts, self.ids = self.read_instance()
self.train_texts, self.train_ids, self.dev_texts, self.dev_ids, self.test_texts, self.test_ids = self.sample_split(
)
else: # inference use
self.char_alphabet = Alphabet('char', keep_growing=False)
self.intent_alphabet = Alphabet('intent', keep_growing=False)
self.label_alphabet = Alphabet('label',
label=True,
keep_growing=False)
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250 #句子最大长度
self.number_normalized = True #是否将数字归一化
self.norm_word_emb = True #是否将词向量归一化
self.word_alphabet = Alphabet('word') #word的词表与id
self.label_alphabet = Alphabet('label', True) #not end "</unk>"
#约定标注方式
self.tagScheme = "NoSeg"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.word_emb_dim = 50
self.pretrain_word_embedding = None
self.label_size = 0
self.word_alphabet_size = 0
self.label_alphabet_size = 0
### hyperparameters
self.HP_iteration = 200
self.HP_batch_size = 32 # 1
self.HP_hidden_dim = 200
self.HP_dropout = 0.3
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_gpu = True # true
self.HP_lr = 0.01
self.HP_lr_decay = 0.05
self.weight_decay = 0.00000005
self.use_clip = False
self.HP_clip = 5.0
self.HP_momentum = 0 #控制优化器的一个超参
self.random_seed = 100
# @Last Modified time: 2017-07-15 17:13:30
import sys
import numpy as np
from utils.alphabet import Alphabet
from utils.data_processor import *
from model.Model import *
from utils.keras_utils import padding
from utils.metric import *
from keras.callbacks import ModelCheckpoint
import tensorflow as tf
from keras.backend.tensorflow_backend import set_session
# from keras.utils.vis_utils import plot_model
word_alphabet = Alphabet('word')
char_alphabet = Alphabet('char')
nb_epoch = 100
use_char = True
mask_zero = True
BILSTM = True
DropProb = 0.2
case_sense = True
batch_size = 128
grad_discent = "adam"
lstm_average = False
label_type = 'BMES'
char_emb_dims = 50
nb_filter = 100
filter_length = 3
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_word_emb = False
self.norm_char_emb = False
self.norm_trans_emb = False
self.word_alphabet = Alphabet('word')
self.char_alphabet = Alphabet('character')
self.translation_alphabet = Alphabet('translation')
self.translation_id_format = {}
self.feature_name = []
self.feature_alphabets = []
self.feature_num = len(self.feature_alphabets)
self.feat_config = None
self.label_alphabet = Alphabet('label', True)
self.tagScheme = "NoSeg" ## BMES/BIO
self.seg = True
### I/O
self.train_dir = None
self.dev_dir = None
self.test_dir = None
self.raw_dir = None
self.trans_dir = None
self.decode_dir = None
self.dset_dir = None ## data vocabulary related file
self.model_dir = None ## model save file
self.load_model_dir = None ## model load file
self.word_emb_dir = None
self.char_emb_dir = None
self.trans_embed_dir = None
self.feature_emb_dirs = []
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.pretrain_word_embedding = None
self.pretrain_char_embedding = None
self.pretrain_trans_embedding = None
self.pretrain_feature_embeddings = []
self.label_size = 0
self.word_alphabet_size = 0
self.char_alphabet_size = 0
self.label_alphabet_size = 0
self.trans_alphabet_size = 0
self.feature_alphabet_sizes = []
self.feature_emb_dims = []
self.norm_feature_embs = []
self.word_emb_dim = 50
self.char_emb_dim = 30
self.trans_emb_dim = 100
###Networks
self.word_feature_extractor = "LSTM" ## "LSTM"/"CNN"/"GRU"/
self.use_char = True
self.char_seq_feature = "CNN" ## "LSTM"/"CNN"/"GRU"/None
self.use_trans = True
self.use_crf = True
self.nbest = None
## Training
self.average_batch_loss = False
self.optimizer = "SGD" ## "SGD"/"AdaGrad"/"AdaDelta"/"RMSProp"/"Adam"
self.status = "train"
### Hyperparameters
self.HP_cnn_layer = 4
self.HP_iteration = 100
self.HP_batch_size = 10
self.HP_char_hidden_dim = 50
self.HP_trans_hidden_dim = 50
self.HP_hidden_dim = 200
self.HP_dropout = 0.5
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_gpu = False
self.HP_lr = 0.015
self.HP_lr_decay = 0.05
self.HP_clip = None
self.HP_momentum = 0
self.HP_l2 = 1e-8
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = False
self.norm_word_emb = True
self.norm_biword_emb = True
self.word_alphabet = Alphabet('word')
self.biword_alphabet = Alphabet('biword')
self.pos_alphabet = Alphabet('pos')
self.label_alphabet = Alphabet('label', True)
self.tagScheme = "NoSeg"
self.char_features = "LSTM"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.use_bigram = False
self.word_emb_dim = 50
self.biword_emb_dim = 50
self.pretrain_word_embedding = None
self.pretrain_biword_embedding = None
self.label_size = 0
self.word_alphabet_size = 0
self.biword_alphabet_size = 0
self.label_alphabet_size = 0
# hyperparameters
self.HP_iteration = 100
self.HP_batch_size = 16
self.HP_char_hidden_dim = 50
self.HP_hidden_dim = 200
self.HP_dropout = 0.2
self.HP_lstmdropout = 0
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_gpu = False
self.HP_lr = 0.015
self.HP_lr_decay = 0.05
self.HP_clip = 5.0
self.HP_momentum = 0
# attention
self.tencent_word_embed_dim = 200
self.pos_embed_dim = 200
self.cross_domain = False
self.cross_test = False
self.use_san = False
self.use_cnn = False
self.use_attention = True
self.pos_to_idx = {}
self.external_pos = {}
self.token_replace_prob = {}
self.use_adam = False
self.use_bert = False
self.use_warmup_adam = False
self.use_sgd = False
self.use_adadelta = False
self.use_window = True
self.mode = 'train'
self.use_tencent_dic = False
# cross domain file
self.computer_file = ""
self.finance_file = ""
self.medicine_file = ""
self.literature_file = ""
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_word_emb = False
self.word_alphabet = Alphabet('word')
self.label = [
"O", "B-A", "I-A", "B-O", "I-O", "B-E", "I-E", "B-T", "I-T", "B-C",
"I-C"
]
self.label_alphabet = Alphabet('label', True)
self.sentence_type_alphabet = Alphabet('sentence', True)
self.tagScheme = "NoSeg" ## BMES/BIO
self.seg = True
### I/O
self.train_dir = None
self.dev_dir = None
self.test_dir = None
self.raw_dir = None
self.decode_dir = None
self.dset_dir = None ## data vocabulary related file
self.model_dir = None ## model save file
self.load_model_dir = None ## model load file
self.word_emb_dir = None
self.word_emb_file = None
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.pretrain_word_embedding = None
self.use_pre_trained_model = None
self.word_alphabet_size = 0
self.opinion_label_alphabet_size = 0
self.evidence_label_alphabet_size = 0
self.sentence_alphabet_size = 0
self.word_emb_dim = 50
self.lstm_input_size = 50
###Networks
self.word_feature_extractor = "LSTM" ## "LSTM"/"CNN"/"GRU"/
self.use_crf = True
self.nbest = None
## Training
self.average_batch_loss = False
self.optimizer = "SGD" ## "SGD"/"AdaGrad"/"AdaDelta"/"RMSProp"/"Adam"
self.status = "train"
### Hyperparameters
self.HP_iteration = 100
self.HP_batch_size = 10
self.HP_hidden_dim = 200
self.HP_attention_query_input_dim = 200
self.HP_dropout = 0.5
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_gpu = False
self.HP_lr = 0.015
self.HP_lr_decay = 0.05
self.HP_clip = None
self.HP_momentum = 0
self.HP_l2 = 1e-8
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_word_emb = True
self.norm_biword_emb = True
self.norm_gaz_emb = False
self.word_alphabet = Alphabet('word')
self.biword_alphabet = Alphabet('biword')
self.char_alphabet = Alphabet('character')
self.label_alphabet = Alphabet('label', True)
#self.simi_alphabet = Alphabet('simi') #添加计算相似度词语的信息
self.gaz_lower = False
self.gaz = Gazetteer(self.gaz_lower)
self.gaz_alphabet = Alphabet('gaz')
self.gaz_count = {}
self.gaz_split = {}
self.biword_count = {}
self.HP_fix_gaz_emb = False
self.HP_use_gaz = True
self.HP_use_count = False
self.tagScheme = "NoSeg"
self.char_features = "LSTM"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.train_split_index = []
self.dev_split_index = []
self.use_bigram = True
self.word_emb_dim = 200
self.biword_emb_dim = 200
self.char_emb_dim = 30
self.gaz_emb_dim = 200
self.gaz_dropout = 0.5
self.pretrain_word_embedding = None
self.pretrain_biword_embedding = None
self.pretrain_gaz_embedding = None
self.label_size = 0
self.word_alphabet_size = 0
self.biword_alphabet_size = 0
self.char_alphabet_size = 0
self.label_alphabet_size = 0
#设置词典相似度相关的参数
self.simi_dic_emb = None #设置相似度的嵌入值
self.simi_dic_dim = 10 #设置相似度向量的纬度
self.use_dictionary = False # 设置当前是否使用词典
self.simi_list = [] #存储当前的每个字对应的相似度值
# self.use_gazcount = 'True'
### hyperparameters
self.HP_iteration = 60
self.HP_batch_size = 10
self.HP_char_hidden_dim = 50
self.HP_hidden_dim = 128
self.HP_dropout = 0.5
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_use_char = False
self.HP_gpu = True
self.HP_lr = 0.015
self.HP_lr_decay = 0.05
self.HP_clip = 5.0
self.HP_momentum = 0
self.HP_num_layer = 4
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_word_emb = True
self.norm_biword_emb = True
self.norm_gaz_emb = False
self.word_alphabet = Alphabet('word')
self.biword_alphabet = Alphabet('biword')
self.char_alphabet = Alphabet('character')
# self.word_alphabet.add(START)
# self.word_alphabet.add(UNKNOWN)
# self.char_alphabet.add(START)
# self.char_alphabet.add(UNKNOWN)
# self.char_alphabet.add(PADDING)
self.label_alphabet = Alphabet('label', True)
self.gaz_lower = False
self.gaz = Gazetteer(self.gaz_lower)
self.gaz_alphabet = Alphabet('gaz')
self.HP_fix_gaz_emb = False
self.HP_use_gaz = True
self.tagScheme = "NoSeg"
self.char_features = "LSTM"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.use_bigram = True
self.word_emb_dim = 50
self.biword_emb_dim = 50
self.char_emb_dim = 30
self.gaz_emb_dim = 50
self.gaz_dropout = 0.5
self.pretrain_word_embedding = None
self.pretrain_biword_embedding = None
self.pretrain_gaz_embedding = None
self.label_size = 0
self.word_alphabet_size = 0
self.biword_alphabet_size = 0
self.char_alphabet_size = 0
self.label_alphabet_size = 0
### hyperparameters
self.HP_iteration = 100
self.HP_batch_size = 10
self.HP_char_hidden_dim = 50
self.HP_hidden_dim = 200
self.HP_dropout = 0.5
self.HP_lstm_layer = 1
self.HP_bilstm = True
self.HP_use_char = False
self.HP_gpu = False
self.HP_lr = 0.015
self.HP_lr_decay = 0.05
self.HP_clip = 5.0
self.HP_momentum = 0
def __init__(self, args):
super(Data, self).__init__()
self.args = args
self.data_dir = args.data_dir # './data/gene_term_format_by_sentence.json'
self.data_ratio = (0.9, 0.05, 0.05) # total 2000
self.model_save_dir = args.savemodel # './saves/model/'
self.output_dir = args.output # './saves/output/'
self.data_save_file = args.savedset # './saves/data/dat.pkl'
self.pos_as_feature = args.use_pos
self.use_elmo = args.use_elmo
self.elmodim = args.elmodim
self.pos_emb_dim = args.posdim
self.useSpanLen = args.use_len
self.use_sentence_att = args.use_sent_att
self.use_char = True
self.ranking = 1
self.word_alphabet = Alphabet('word')
self.char_alphabet = Alphabet('character')
self.ptag_alphabet = Alphabet('tag')
self.label_alphabet = Alphabet('label', label=True)
self.seqlabel_alphabet = Alphabet('span_label', label=True)
self.word_alphabet_size = 0
self.char_alphabet_size = 0
self.ptag_alphabet_size = 0
self.label_alphabet_size = 0
self.seqlabel_alphabet_size = 0
self.max_sentence_length = 500
self.term_truples = []
self.sent_texts = []
self.chars = []
self.lengths = []
self.ptags = []
self.seq_labels = []
self.word_ids_sent = []
self.char_id_sent = []
self.tag_ids_sent = []
self.label_ids_sent = []
self.seq_labels_ids = []
self.longSpan = True
self.shortSpan = True
self.termratio = args.term_ratio
self.term_span = args.max_length
self.word_feature_extractor = "LSTM" ## "LSTM"/"CNN"/"GRU"/
self.char_feature_extractor = "CNN" ## "LSTM"/"CNN"/"GRU"/None
# training
self.optimizer = 'Adam' # "SGD"/"AdaGrad"/"AdaDelta"/"RMSProp"/"Adam"
self.training = True
self.average_batch_loss = True
self.evaluate_every = args.evaluate_every # 10 # evaluate every n batches
self.print_every = args.print_every
self.silence = True
self.earlystop = args.early_stop
# Embeddings
self.word_emb_dir = args.wordemb # './data/glove.6B.100d.txt' # None #'../data/glove.6b.100d.txt'
self.char_emb_dir = args.charemb
self.word_emb_dim = 50
self.char_emb_dim = 30
self.spamEm_dim = 30
self.norm_word_emb = False
self.norm_char_emb = False
self.pretrain_word_embedding = None
self.pretrain_char_embedding = None
# HP
self.HP_char_hidden_dim = 50
self.HP_hidden_dim = 100
self.HP_cnn_layer = 2
self.HP_batch_size = 100
self.HP_epoch = 100
self.HP_lr = args.lr
self.HP_lr_decay = 0.05
self.HP_clip = None
self.HP_l2 = 1e-8
self.HP_dropout = args.dropout
self.HP_lstm_layer = 2
self.HP_bilstm = True
self.HP_gpu = args.use_gpu # False#True
self.HP_term_span = 6
self.HP_momentum = 0
# init data
self.build_vocabs()
self.all_instances = self.load_data()
self.load_pretrain_emb()
def __init__(self):
self.MAX_SENTENCE_LENGTH = 250
self.MAX_WORD_LENGTH = -1
self.number_normalized = True
self.norm_char_emb = True
self.norm_bichar_emb = True
self.norm_gaz_emb = False
self.use_single = False
self.char_alphabet = Alphabet('char')
self.bichar_alphabet = Alphabet('bichar')
self.label_alphabet = Alphabet('label', True)
self.gaz_lower = False
self.gaz = Gazetteer(self.gaz_lower, self.use_single)
self.gaz_alphabet = Alphabet('gaz')
self.HP_fix_gaz_emb = False
self.HP_use_gaz = True
self.tagScheme = "NoSeg"
self.train_texts = []
self.dev_texts = []
self.test_texts = []
self.raw_texts = []
self.train_Ids = []
self.dev_Ids = []
self.test_Ids = []
self.raw_Ids = []
self.use_bichar = False
self.char_emb_dim = 50
self.bichar_emb_dim = 50
self.gaz_emb_dim = 50
self.posi_emb_dim = 30
self.gaz_dropout = 0.5
self.pretrain_char_embedding = None
self.pretrain_bichar_embedding = None
self.pretrain_gaz_embedding = None
self.label_size = 0
self.char_alphabet_size = 0
self.bichar_alphabet_size = 0
self.character_alphabet_size = 0
self.label_alphabet_size = 0
# hyper parameters
self.HP_iteration = 100
self.HP_batch_size = 1
# self.HP_char_hidden_dim = 50 # int. Character hidden vector dimension for character sequence layer.
self.HP_hidden_dim = 200 # int. Char hidden vector dimension for word sequence layer.
self.HP_dropout = 0.5 # float. Dropout probability.
self.HP_lstm_layer = 1 # int. LSTM layer number for word sequence layer.
self.HP_bilstm = True # boolen. If use bidirection lstm for word seuquence layer.
self.HP_gpu = False
# Word level LSTM models (e.g. char LSTM + word LSTM + CRF) would prefer a `lr` around 0.015.
# Word level CNN models (e.g. char LSTM + word CNN + CRF) would prefer a `lr` around 0.005 and with more iterations.
self.HP_lr = 0.015
self.HP_lr_decay = 0.05 # float. Learning rate decay rate, only works when optimizer=SGD.
self.HP_clip = 1.0 # float. Clip the gradient which is larger than the setted number.
self.HP_momentum = 0 # float. Momentum
self.HP_use_posi = False
self.HP_num_layer = 4
self.HP_rethink_iter = 2
self.model_name = 'CNN_model'
self.posi_alphabet_size = 0
