知识图谱入门之---yedda标注

下载地址：github.

数据标注工具YEDDA_墨读的博客-CSDN博客_yedda标注
  学习笔记之——YEDDA_小樊努力努力再努力的博客-CSDN博客_yedda标注

 运行YEDDA-master文件夹下的YEDDA.py文件即可。最新后的支持python3

yedda可以导出BMES和BIO格式

 可以将其转换为BIEOS格式：参考

【BMES-->BIEOS】

f = open(r'H:/output/test.txt', 'r', encoding='utf-8')
f1 = open(r'H:/output/bioes.txt', 'w+', encoding='utf-8')
str1 = []

for line in f.readlines():
    # print(list(line))
    if line != "\n":
        line1 = line.split()
        str2 = line1[0]
        for i in range(1, len(line1)):
            line2 = list(line1[i])
            if line2[0] == "M":
                line2[0] = "I"
            str3 = ''
            for i in line2:
                str3 = str3 + i
            str2 = str2 + ' ' + str3
        print(str2)
        str1.append(str2)
    else:
        str1.append(line)
for j in str1:
    f1.write(j)
    f1.write("\n")

【BIO-->BMES】

path = r'H:/output/bio.txt'
res_path = r'H:/output/bems.txt'

f = open(path, encoding='utf-8')
f1 = open(res_path, 'w+', encoding='utf_8')

sentences = []
sentence = []
label_set = set()
cnt_line = 0
for line in f:
    cnt_line += 1
    if len(line) == 0 or line[0] == '\n':
        if len(sentence) > 0:
            sentences.append(sentence)
            print(sentence)
            sentence = []
        continue
    splits = line.split(' ')
    sentence.append([splits[0], splits[-1][:-1]])
    label_set.add(splits[-1])

if len(sentence) > 0:
    sentences.append(sentence)
    sentence = []
f.close()

for sen in sentences:
    i = 0
    for index, word in enumerate(sen):
        char = word[0]
        label = word[1]
        if index < len(sen) - 1:
            if (label[0] == 'B'):
                if sen[index + 1][1][0] == 'I':
                    label = label
                elif sen[index + 1][1][0] == 'O':
                    label = 'S' + label[1:]
            elif (label[0] == 'I'):
                if sen[index + 1][1][0] == 'I':
                    label = 'M' + label[1:]
                if sen[index + 1][1][0] == 'O' or sen[index + 1][1][0] == 'B':
                    label = 'E' + label[1:]
            elif (label[0] == 'O'):
                label = label
        else:
            if (label[0] == 'B'):
                label = 'S' + label[1:]
            elif (label[0] == 'I'):
                label = 'E' + label[1:]
            elif (label[0] == 'O'):
                label = label

        f1.write(f'{char} {label}\n')
    f1.write('\n')
f1.close()