大话Word2vec

Skip-gram和CBOW简单区别

Skip-gram：词预测上下文
CBOW：上下文预测词

1. 输入一个词，预测下一个词
   
2. 一个词预测多个词
   

CBOW 多个词预测一个词

3. 欧氏距离
5. 余弦相似度

TF-idf

其中nd等于文档总数，df(t)为包含该词条的文档数
例子：

#训练word2vector代码

!echo '数据集行数:'
!wc -l 'bioCorpus_5000.txt'
!echo '======'
!echo '数据集前10行'
!head -10 'bioCorpus_5000.txt'

### 2.2. Word2vec 训练

import nltk
from gensim.models import word2vec

# 用生成器的方式读取文件里的句子
# 适合读取大容量文件，而不用加载到内存
class MySentences(object):
    def __init__(self, fname):
        self.fname = fname
 
    def __iter__(self):
        for line in open(self.fname,'r'):
            yield line.split()

# 模型训练函数
def w2vTrain(f_input, model_output):         
    sentences = MySentences(DataDir+f_input)
    w2v_model = word2vec.Word2Vec(sentences, 
                                  min_count = MIN_COUNT, 
                                  workers = CPU_NUM, 
                                  size = VEC_SIZE,
                                  window = CONTEXT_WINDOW
                                 )
    w2v_model.save(ModelDir+model_output)


# 训练
DataDir = "./"
ModelDir = "./"
MIN_COUNT = 4
CPU_NUM = 2 # 需要预先安装 Cython 以支持并行
VEC_SIZE = 20
CONTEXT_WINDOW = 5 # 提取目标词上下文距离最长5个词

f_input = "bioCorpus_5000.txt"
model_output = "test_w2v_model"

w2vTrain(f_input, model_output)

### 2.3. 查看结果

# 加载模型
w2v_model = word2vec.Word2Vec.load(ModelDir+model_output)

w2v_model.most_similar('body') # 结果一般

w2v_model.most_similar('heart') # 结果太差

# 数据集不够大时，停止词太多，解决方法：去除停止词

# 停止词
from nltk.corpus import stopwords

StopWords = stopwords.words('english')

StopWords[:20]

# 重新训练
# 模型训练函数
def w2vTrain_removeStopWords(f_input, model_output):         
    sentences = list(MySentences(DataDir+f_input))
    for idx,sentence in enumerate(sentences):
        sentence = [w for w in sentence if w not in StopWords]
        sentences[idx]=sentence
    w2v_model = word2vec.Word2Vec(sentences, min_count = MIN_COUNT, 
                                  workers = CPU_NUM, size = VEC_SIZE)
    w2v_model.save(ModelDir+model_output)

w2vTrain_removeStopWords(f_input, model_output)
w2v_model = word2vec.Word2Vec.load(ModelDir+model_output)

w2v_model.most_similar('heart') # 结果一般

结果：

[('formation', 0.9698415994644165),
 ('blood', 0.965557336807251),
 ('metabolism', 0.9630600214004517),
 ('changes', 0.9596229195594788),
 ('study', 0.9578454494476318),
 ('brain', 0.9577423334121704),
 ('liver', 0.957546591758728),
 ('synthesis', 0.9570505619049072),
 ('method', 0.9542899131774902),
 ('renal', 0.9542509913444519)]
 

TextRank

https://www.cnblogs.com/motohq/p/11887420.html