深度学习是一种“端到端”的模型,所谓端到端就是能够将原始数据和标签输入,然后让模型自己完成一切过程-包括特征的提取、模型的学习。。而回顾我们做中文情感分类的过程,一般都是“分词——词向量——句向量(LSTM)——分类”这么几个步骤。虽然很多时候这种模型已经达到了state of art的效果,但是有些疑问还是需要进一步测试解决的。对于中文来说,字才是最低粒度的文字单位,因此从“端到端”的角度来看,应该将直接将句子以字的方式进行输入,而不是先将句子分好词。那到底有没有分词的必要性呢?本文测试比较了字one hot、字向量、词向量三者之间的效果。
模型测试
本文测试了三个模型,或者说是三套框架
1:one-hot 以字为单位,不分词,将每个句子截断为200字(不够则补齐空字符串),然后将句子以字one-hot的矩阵形式输入lstm模型中进行学习分类
2:one embedding:以字为单位,不分词,将每个句子截断为200字(不够则补齐空字符串),然后将句子以字-字向量的矩阵形式输入lstm模型中进行学习分类
3:word-embedding:以词的为单位,分词,将每隔句子截断为100词,然后将句子以词-词向量的矩阵形式输入到LSTM模型中进行学习分类。
其中所用的LSTM模型结构是类似的。意外的是,三个模型取得了类似的结果。
针对one-hot的理解
到底该不该舍弃one-hot?????
模型1:one hot
# -*- coding:utf-8 -*-
'''
one hot测试
在GTX960上,约100s一轮
经过90轮迭代,训练集准确率为96.60%,测试集准确率为89.21%
Dropout不能用太多,否则信息损失太严重
'''
import numpy as np
import pandas as pd
pos = pd.read_excel('pos.xls', header=None)
pos['label'] = 1
neg = pd.read_excel('neg.xls', header=None)
neg['label'] = 0
all_ = pos.append(neg, ignore_index=True)
maxlen = 200 #截断字数
min_count = 20 #出现次数少于该值的字扔掉。这是最简单的降维方法
content = ''.join(all_[0])
abc = pd.Series(list(content)).value_counts()
abc = abc[abc >= min_count]
abc[:] = range(len(abc))
word_set = set(abc.index)
def doc2num(s, maxlen):
s = [i for i in s if i in word_set]
s = s[:maxlen]
return list(abc[s])
all_['doc2num'] = all_[0].apply(lambda s: doc2num(s, maxlen))
#手动打乱数据
#当然也可以把这部分加入到生成器中
idx = range(len(all_))
np.random.shuffle(idx)
all_ = all_.loc[idx]
#按keras的输入要求来生成数据
x = np.array(list(all_['doc2num']))
y = np.array(list(all_['label']))
y = y.reshape((-1,1)) #调整标签形状
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.layers import LSTM
import sys
sys.setrecursionlimit(10000) #增大堆栈最大深度(递归深度),据说默认为1000,报错
#建立模型
model = Sequential()
model.add(LSTM(128, input_shape=(maxlen,len(abc))))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
#单个one hot矩阵的大小是maxlen*len(abc)的,非常消耗内存
#为了方便低内存的PC进行测试,这里使用了生成器的方式来生成one hot矩阵
#仅在调用时才生成one hot矩阵
#可以通过减少batch_size来降低内存使用,但会相应地增加一定的训练时间
batch_size = 128
train_num = 15000
#不足则补全0行
gen_matrix = lambda z: np.vstack((np_utils.to_categorical(z, len(abc)), np.zeros((maxlen-len(z), len(abc)))))
def data_generator(data, labels, batch_size):
batches = [range(batch_size*i, min(len(data), batch_size*(i+1))) for i in range(len(data)/batch_size+1)]
while True:
for i in batches:
xx = np.zeros((maxlen, len(abc)))
xx, yy = np.array(map(gen_matrix, data[i])), labels[i]
yield (xx, yy)
model.fit_generator(data_generator(x[:train_num], y[:train_num], batch_size), samples_per_epoch=train_num, nb_epoch=30)
model.evaluate_generator(data_generator(x[train_num:], y[train_num:], batch_size), val_samples=len(x[train_num:]))
def predict_one(s): #单个句子的预测函数
s = gen_matrix(doc2num(s, maxlen))
s = s.reshape((1, s.shape[0], s.shape[1]))
return model.predict_classes(s, verbose=0)[0][0]
模型2:one embedding
# -*- coding:utf-8 -*-
'''
one embedding测试
在GTX960上,36s一轮
经过30轮迭代,训练集准确率为95.95%,测试集准确率为89.55%
Dropout不能用太多,否则信息损失太严重
'''
import numpy as np
import pandas as pd
pos = pd.read_excel('pos.xls', header=None)
pos['label'] = 1
neg = pd.read_excel('neg.xls', header=None)
neg['label'] = 0
all_ = pos.append(neg, ignore_index=True)
maxlen = 200 #截断字数
min_count = 20 #出现次数少于该值的字扔掉。这是最简单的降维方法
content = ''.join(all_[0])
abc = pd.Series(list(content)).value_counts()
abc = abc[abc >= min_count]
abc[:] = range(1, len(abc)+1)
abc[''] = 0 #添加空字符串用来补全
word_set = set(abc.index)
def doc2num(s, maxlen):
s = [i for i in s if i in word_set]
s = s[:maxlen] + ['']*max(0, maxlen-len(s))
return list(abc[s])
all_['doc2num'] = all_[0].apply(lambda s: doc2num(s, maxlen))
#手动打乱数据
idx = range(len(all_))
np.random.shuffle(idx)
all_ = all_.loc[idx]
#按keras的输入要求来生成数据
x = np.array(list(all_['doc2num']))
y = np.array(list(all_['label']))
y = y.reshape((-1,1)) #调整标签形状
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout, Embedding
from keras.layers import LSTM
#建立模型
model = Sequential()
model.add(Embedding(len(abc), 256, input_length=maxlen))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
batch_size = 128
train_num = 15000
model.fit(x[:train_num], y[:train_num], batch_size = batch_size, nb_epoch=30)
model.evaluate(x[train_num:], y[train_num:], batch_size = batch_size)
def predict_one(s): #单个句子的预测函数
s = np.array(doc2num(s, maxlen))
s = s.reshape((1, s.shape[0]))
return model.predict_classes(s, verbose=0)[0][0]
模型3:word embedding
# -*- coding:utf-8 -*-
'''
word embedding测试
在GTX960上,18s一轮
经过30轮迭代,训练集准确率为98.41%,测试集准确率为89.03%
Dropout不能用太多,否则信息损失太严重
'''
import numpy as np
import pandas as pd
import jieba
pos = pd.read_excel('pos.xls', header=None)
pos['label'] = 1
neg = pd.read_excel('neg.xls', header=None)
neg['label'] = 0
all_ = pos.append(neg, ignore_index=True)
all_['words'] = all_[0].apply(lambda s: list(jieba.cut(s))) #调用结巴分词
maxlen = 100 #截断词数
min_count = 5 #出现次数少于该值的词扔掉。这是最简单的降维方法
content = []
for i in all_['words']:
content.extend(i)
abc = pd.Series(content).value_counts()
abc = abc[abc >= min_count]
abc[:] = range(1, len(abc)+1)
abc[''] = 0 #添加空字符串用来补全
word_set = set(abc.index)
def doc2num(s, maxlen):
s = [i for i in s if i in word_set]
s = s[:maxlen] + ['']*max(0, maxlen-len(s))
return list(abc[s])
all_['doc2num'] = all_['words'].apply(lambda s: doc2num(s, maxlen))
#手动打乱数据
idx = range(len(all_))
np.random.shuffle(idx)
all_ = all_.loc[idx]
#按keras的输入要求来生成数据
x = np.array(list(all_['doc2num']))
y = np.array(list(all_['label']))
y = y.reshape((-1,1)) #调整标签形状
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout, Embedding
from keras.layers import LSTM
#建立模型
model = Sequential()
model.add(Embedding(len(abc), 256, input_length=maxlen))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
batch_size = 128
train_num = 15000
model.fit(x[:train_num], y[:train_num], batch_size = batch_size, nb_epoch=30)
model.evaluate(x[train_num:], y[train_num:], batch_size = batch_size)
def predict_one(s): #单个句子的预测函数
s = np.array(doc2num(list(jieba.cut(s)), maxlen))
s = s.reshape((1, s.shape[0]))
return model.predict_classes(s, verbose=0)[0][0]