【NLP_命名实体识别】CRF++使用流程

重要参考

用CRF做命名实体识别(一) - 简书 (jianshu.com)https://www.jianshu.com/p/12f2cdd86679(8条消息) 【windows下CRF++的安装与使用】_feng_zhiyu的博客-CSDN博客_crf++安装https://blog.csdn.net/feng_zhiyu/article/details/80793316

代码实践

• {B, M, E, S} 格式：B表示实体首字，M表示实体中字，E表示实体尾字，S表示单字
• 注意：各种编码/解码细节

生成训练/测试数据

• 生成训练数据/测试数据均为适合CRF++的格式

# -*- coding: utf8  -*-

import sys
home_dir = "D:\Desktop\新Asian-Elephant\毕业\CRF\CRF++-0.58\YWP\\199801\\"

def splitWord(words):
    uni = words.encode('utf-8').decode('utf-8')
    li = list()
    for u in uni:
        li.append(str(u).encode('utf-8'))
    return li

# 4 tag: {B, M, E, S}
def get4Tag(li):
    length = len(li)
    # print length
    if length == 1:
        return ['S']
    elif length == 2:
        return ['B', 'E']
    elif length > 2:
        li = list()
        li.append('B')
    for i in range(0, length - 2):
        li.append('M')
    li.append('E')
    return li

def saveDataFile(trainobj, testobj, isTest, word, handle, tag):
    if isTest:
        saveTrainFile(testobj, word, handle, tag)
    else:
        saveTrainFile(trainobj, word, handle, tag)

def saveTrainFile(fiobj, word, handle, tag):
    if len(word) > 0:
        wordli = splitWord(word)
        tag == '4'
        tagli = get4Tag(wordli)
        for i in range(0, len(wordli)):
            w = wordli[i]
            h = handle
            t = tagli[i]
            w=w.decode('utf-8')
            fiobj.write(str(w) + '\t' + h + '\t' + t + '\n')
    else:
        # print 'New line'
        fiobj.write('\n')

# B,M,M1,M2,M3,E,S
def convertTag(tag):
    fiobj = open(home_dir + 'people-daily.txt', 'r')
    trainobj = open(home_dir +  'train.data', 'w',encoding='UTF-8')
    testobj = open(home_dir + 'test.data', 'w',encoding='UTF-8')

    arr = fiobj.readlines()
    i = 0
    for a in arr:
        i += 1
        a = a.strip('\r\n\t ')
        if a == "": continue
        words = a.split(" ")
        test = False
        if i % 10 == 0:
            test = True
        for word in words:
            # print "---->", word
            word = word.strip('\t ')
            if len(word) > 0:
                i1 = word.find('[')
            if i1 >= 0:
                word = word[i1 + 1:]
            i2 = word.find(']')
            if i2 > 0:
                w = word[:i2]
            word_hand = word.split('/')
            # print "----",word
            #print("word_hand[0]:",word_hand[0])
            #print("word_hand[1]:", word_hand[1])
            #print('word_hand:',word_hand)
            #print('len(word_hand):',len(word_hand))
        w, h = word_hand[0],word_hand[1] #w, h = word_hand
        # print w,h
        if h == 'nr':  # ren min
                # print 'NR',w
                if w.find('·') >= 0:
                    tmpArr = w.split('·')
                    for tmp in tmpArr:
                        saveDataFile(trainobj, testobj, test, tmp, h, tag)
                continue
        if h != 'm':
                saveDataFile(trainobj, testobj, test, w, h, tag)

        if h == 'w':
                saveDataFile(trainobj, testobj, test, "", "", tag)  # split

    trainobj.flush()
    testobj.flush()

# sys.argv[0]表示代码本身文件路径
# Sys.argv[ ]其实就是一个列表，里边的项为用户输入的参数，关键就是要明白这参数是从程序外部输入的

if __name__ == '__main__':

    #tag = sys.argv[0]
    convertTag(4)

创建特征模板

• 创建由指定特征组成的模板→存至template文件

简易模板

模型训练与测试

简易版

• 命令行下，训练模型→model

crf_learn -a MIRA template train.data model

• 命令行下，评估模型

crf_test -m model test.data >> output.txt

完整版

• 命令行下，训练模型→model
• template：模板文件，train.data：生成的训练数据，4_model ：模型

crf_learn -f 3 -c 4.0 template train.data 4_model > 4_train.rst 

crf_test -m 4_model test.data > 4_test.rst

评估模型

import sys

if __name__ == "__main__":
    try:
        file = open(sys.argv[1], "r",encoding='UTF-8')
    except:
        print
        ("result file is not specified, or open failed!")
        sys.exit()

    wc_of_test = 0
    wc_of_gold = 0
    wc_of_correct = 0
    flag = True

    for l in file:
        if l == '\n': continue

        _, _, g, r = l.strip().split()

        if r != g:
            flag = False

        if r in ('E', 'S'):
            wc_of_test += 1
            if flag:
                wc_of_correct += 1
            flag = True

        if g in ('E', 'S'):
            wc_of_gold += 1

    print("WordCount from test result:", wc_of_test)
    print("WordCount from golden data:", wc_of_gold)
    print("WordCount of correct segs :", wc_of_correct)

    # 查全率
    P = wc_of_correct / float(wc_of_test)
    # 查准率，召回率
    R = wc_of_correct / float(wc_of_gold)

    print("P = %f, R = %f, F-score = %f" % (P, R, (2 * P * R) / (P + R)))

• 命令行下，运行评估模型的文件F-value.py

python F-value.py 4_test.rst

简易评估结果