NLP基础之词性标注代码实现

# 数据集已对每个词进行了标注
#生成 词库，词标签，词性标签
word2id, id2word = {
   },{
   }
tag2id, id2tag = {
   }, {
   }

for line in open('traindata.txt'):
    item = line.split('/')
    word, tag = item[0], item[1].rstrip()
    if word not in word2id:
        word2id[word] = len(word2id)
        id2word[len(word2id)] = word
    if tag not in tag2id:
        tag2id[tag] = len(tag2id)
        id2tag[len(id2tag)] = tag
        
        
M = len(word2id)
N = len(tag2id)

# 构建pi，A, B
import numpy as np
pi = np.zeros(N)  # 每个tag（词性）出现在句首的概率
A = np.zeros