命名实体识别

于 2021-02-19 15:28:21 发布
阅读量422 收藏
点赞数
分类专栏： 命名实体识别 nlp python
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_42075890/article/details/113865193
版权

Kashgari BERT 命名实体识别 中文数据集 模型训练
关键词由CSDN通过智能技术生成

命名实体识别

简单方法：kashgari实现，类似于搭积木

环境

tensorflow 1.15.0
pip install ‘kashgari>=1.0.0,<2.0.0’ current version
下载bert模型，放在当前项目文件

人民日报数据集

  1. 数据类型（打印部分）
```python
'''
valid_x

[['还', '有', '一', '次', '，', '李', '先', '生', '在', '办', '公', '桌', '旁', '从', '上', '午', '8', '时', '一', '坐', '就', '坐', '到', '了', '下', '午', '4', '时', '，', '连', '饭', '也', '没', '有', '吃', '。'],
['赞', '『', '回', '家', '问', '问', '孙', '子', '』', '（', '人', '民', '论', '坛', '）'],
['温', '家', '宝', '强', '调', '，', '防', '范', '金', '融', '风', '险', '，', '支', '持', '经', '济', '发', '展', '，', '是', '金', '融', '系', '统', '必', '须', '始', '终', '坚', '持', '的', '方', '针', '。'],
['现', '在', '因', '特', '网', '不', '仅', '能', '通', '信', '，', '还', '能', '传', '递', '语', '音', '，', '在', '网', '络', '上', '打', '电', '话', '的', '技', '术', '逐', '渐', '发', '展', '起', '来', '。'],
['其', '中', '，', '反', '对', '官', '僚', '主', '义', '斗', '争', '办', '公', '室', '处', '理', '8', '4', '起', '，', '移', '交', '执', '纪', '执', '法', '的', '5', '0', '起', '，', '为', '国', '家', '挽', '回', '直', '接', '经', '济', '损', '失', '2', '5', '0', '0', '万', '元', '。'],
['下', '岗', '职', '工', '潘', '维', '军', '抱', '着', '出', '生', '才', '5', '0', '天', '的', '女', '儿', '潘', '研', '，', '从', '老', '家', '辽', '宁', '阜', '新', '市', '来', '到', '北', '京', '求', '医', '，', '治', '疗', '右', '下', '眼', '睑', '长', '出', '的', '血', '管', '瘤', '。'],
['例', '如', '，', '茂', '名', '市', '茂', '南', '区', '原', '有', '神', '庙', '近', '二', '百', '座', '。'],
['北', '大', '在', '介', '绍', '西', '方', '学', '术', '方', '面', '起', '了', '领', '先', '的', '作', '用', '，', '在', '以', '西', '方', '的', '治', '学', '方', '法', '整', '理', '中', '国', '传', '统', '学', '术', '的', '工', '作', '上', '，', '也', '做', '出', '了', '显', '著', '的', '贡', '献', '。'],
['爱', '尔', '兰', '共', '和', '军', '于', '去', '年', '7', '月', '宣', '布', '无', '期', '限', '停', '火', '，', '并', '支', '持', '其', '政', '治', '组', '织', '新', '芬', '党', '参', '加', '北', '爱', '和', '平', '谈', '判', '，', '为', '今', '年', '4', '月', '达', '成', '历', '史', '性', '和', '平', '协', '议', '创', '造', '了', '条', '件', '。'],
['表', '现', '在', '学', '风', '上', '，', '根', '本', '谈', '不', '上', '“', '认', '真', '学', '习', '”', '、', '“', '民', '主', '讨', '论', '”', '、', '“', '积', '极', '探', '索', '”', '、', '“', '求', '真', '务', '实', '”', '，', '而', '是', '为', '了', '“', '包', '装', '”', '。']]
--------------------------------------------------
valid_y
[['O', 'O', 'O', 'O', 'O', 'B-PER', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['B-PER', 'I-PER', 'I-PER', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['O', 'O', 'O', 'B-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['O', 'O', 'O', 'O', 'B-PER', 'I-PER', 'I-PER', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-PER', 'I-PER', 'O', 'O', 'O', 'O', 'B-LOC', 'I-LOC', 'B-LOC', 'I-LOC', 'I-LOC', 'O', 'O', 'B-LOC', 'I-LOC', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['O', 'O', 'O', 'B-LOC', 'I-LOC', 'I-LOC', 'B-LOC', 'I-LOC', 'I-LOC', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['B-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-LOC', 'I-LOC', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['B-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ORG', 'I-ORG', 'I-ORG', 'O', 'O', 'B-LOC', 'I-LOC', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O'],
['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O']]
'''
  1. 代码
from kashgari.corpus import ChineseDailyNerCorpus
from kashgari.embeddings import BERTEmbedding
from kashgari.tasks.labeling import BiLSTM_CRF_Model
import kashgari


train_x, train_y = ChineseDailyNerCorpus.load_data('train')
test_x, test_y = ChineseDailyNerCorpus.load_data('test')
valid_x, valid_y = ChineseDailyNerCorpus.load_data('valid')

# print(valid_x[0:5])
# print("-"*50)
# print(valid_y[0:5])

# chinese为bert的预训练模型（chinese-L-12_H768_A-12）
embedding = BERTEmbedding("chinese", sequence_length=10, task=kashgari.LABELING)
model = BiLSTM_CRF_Model(embedding)
model.fit(train_x, train_y, x_validate=valid_x, y_validate=valid_y, epochs=1, batch_size=100)
model.evaluate(test_x, test_y)
  1. 结果
'''
Model: "model_4"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
Input-Token (InputLayer)        [(None, 10)]         0                                            
__________________________________________________________________________________________________
Input-Segment (InputLayer)      [(None, 10)]         0                                            
__________________________________________________________________________________________________
Embedding-Token (TokenEmbedding [(None, 10, 768), (2 16226304    Input-Token[0][0]                
__________________________________________________________________________________________________
Embedding-Segment (Embedding)   (None, 10, 768)      1536        Input-Segment[0][0]              
__________________________________________________________________________________________________
Embedding-Token-Segment (Add)   (None, 10, 768)      0           Embedding-Token[0][0]            
                                                                 Embedding-Segment[0][0]          
__________________________________________________________________________________________________
Embedding-Position (PositionEmb (None, 10, 768)      7680        Embedding-Token-Segment[0][0]    
__________________________________________________________________________________________________
Embedding-Dropout (Dropout)     (None, 10, 768)      0           Embedding-Position[0][0]         
__________________________________________________________________________________________________
Embedding-Norm (LayerNormalizat (None, 10, 768)      1536        Embedding-Dropout[0][0]          
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 10, 768)      2362368     Embedding-Norm[0][0]             
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-1-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 10, 768)      0           Embedding-Norm[0][0]             
                                                                 Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-1-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-1-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-1-MultiHeadSelfAttention-
                                                                 Encoder-1-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-1-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-1-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-1-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-2-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-1-FeedForward-Norm[0][0] 
                                                                 Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-2-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-2-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-2-MultiHeadSelfAttention-
                                                                 Encoder-2-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-2-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-2-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-2-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-3-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-2-FeedForward-Norm[0][0] 
                                                                 Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-3-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-3-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-3-MultiHeadSelfAttention-
                                                                 Encoder-3-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-3-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-3-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-3-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-4-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-3-FeedForward-Norm[0][0] 
                                                                 Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-4-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-4-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-4-MultiHeadSelfAttention-
                                                                 Encoder-4-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-4-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-4-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-4-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-5-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-4-FeedForward-Norm[0][0] 
                                                                 Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-5-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-5-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-5-MultiHeadSelfAttention-
                                                                 Encoder-5-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-5-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-5-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-5-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-6-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-5-FeedForward-Norm[0][0] 
                                                                 Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-6-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-6-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-6-MultiHeadSelfAttention-
                                                                 Encoder-6-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-6-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-6-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-6-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-7-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-6-FeedForward-Norm[0][0] 
                                                                 Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-7-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-7-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-7-MultiHeadSelfAttention-
                                                                 Encoder-7-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-7-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-7-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-7-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-8-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-7-FeedForward-Norm[0][0] 
                                                                 Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-8-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-8-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-8-MultiHeadSelfAttention-
                                                                 Encoder-8-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-8-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-8-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 10, 768)      2362368     Encoder-8-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-9-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 10, 768)      0           Encoder-8-FeedForward-Norm[0][0] 
                                                                 Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 10, 768)      1536        Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward (FeedForw (None, 10, 768)      4722432     Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward-Dropout ( (None, 10, 768)      0           Encoder-9-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-9-FeedForward-Add (Add) (None, 10, 768)      0           Encoder-9-MultiHeadSelfAttention-
                                                                 Encoder-9-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-9-FeedForward-Norm (Lay (None, 10, 768)      1536        Encoder-9-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 10, 768)      2362368     Encoder-9-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 10, 768)      0           Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 10, 768)      0           Encoder-9-FeedForward-Norm[0][0] 
                                                                 Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 10, 768)      1536        Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward (FeedFor (None, 10, 768)      4722432     Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward-Dropout  (None, 10, 768)      0           Encoder-10-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-10-FeedForward-Add (Add (None, 10, 768)      0           Encoder-10-MultiHeadSelfAttention
                                                                 Encoder-10-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-10-FeedForward-Norm (La (None, 10, 768)      1536        Encoder-10-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 10, 768)      2362368     Encoder-10-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 10, 768)      0           Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 10, 768)      0           Encoder-10-FeedForward-Norm[0][0]
                                                                 Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 10, 768)      1536        Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward (FeedFor (None, 10, 768)      4722432     Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward-Dropout  (None, 10, 768)      0           Encoder-11-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-11-FeedForward-Add (Add (None, 10, 768)      0           Encoder-11-MultiHeadSelfAttention
                                                                 Encoder-11-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-11-FeedForward-Norm (La (None, 10, 768)      1536        Encoder-11-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 10, 768)      2362368     Encoder-11-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 10, 768)      0           Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 10, 768)      0           Encoder-11-FeedForward-Norm[0][0]
                                                                 Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 10, 768)      1536        Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward (FeedFor (None, 10, 768)      4722432     Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward-Dropout  (None, 10, 768)      0           Encoder-12-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-12-FeedForward-Add (Add (None, 10, 768)      0           Encoder-12-MultiHeadSelfAttention
                                                                 Encoder-12-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-12-FeedForward-Norm (La (None, 10, 768)      1536        Encoder-12-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-Output (Concatenate)    (None, 10, 3072)     0           Encoder-9-FeedForward-Norm[0][0] 
                                                                 Encoder-10-FeedForward-Norm[0][0]
                                                                 Encoder-11-FeedForward-Norm[0][0]
                                                                 Encoder-12-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
non_masking_layer (NonMaskingLa (None, 10, 3072)     0           Encoder-Output[0][0]             
__________________________________________________________________________________________________
layer_blstm (Bidirectional)     (None, 10, 256)      3277824     non_masking_layer[0][0]          
__________________________________________________________________________________________________
layer_dense (Dense)             (None, 10, 64)       16448       layer_blstm[0][0]                
__________________________________________________________________________________________________
layer_crf_dense (Dense)         (None, 10, 8)        520         layer_dense[0][0]                
__________________________________________________________________________________________________
layer_crf (CRF)                 (None, 10, 8)        64          layer_crf_dense[0][0]            
==================================================================================================
Total params: 104,586,376
Trainable params: 3,294,856
Non-trainable params: 101,291,520
__________________________________________________________________________________________________
209/209 [==============================] - 140s 669ms/step - loss: 1.5892 - accuracy: 0.9473 - val_loss: 11.9012 - val_accuracy: 0.9410
           precision    recall  f1-score   support

      PER     0.8906    0.9167    0.9035       684
      LOC     0.8226    0.8294    0.8260      1096
      ORG     0.7163    0.6807    0.6981       805

micro avg     0.8096    0.8062    0.8079      2585
macro avg     0.8075    0.8062    0.8067      2585


Process finished with exit code 0

'''
zz__2020
关注
专栏目录
【论文笔记】命名实体识别论文
Kaiyuan_sjtu的博客
04-10 8363
写在前面 其实实体识别这块看了挺久了的，今天就来好好聊一聊它。实体识别(Name Entity Recognition)是属于NLP任务中的序列标注问题：给定一个输入句子，要求为句子中的每一个token做实体标注（如人名、组织/机构、地名、日期等等）。 NER算法回顾 明白了NER任务的目的，那我们就来看看具体是怎么实现的。到目前为止，可以大致分为基于规则、基于传统机器学习方法和基于深度学习方法...
NLP从零开始------6基础文本处理之命名实体识别
最新发布
m0_74922316的博客
08-02 1349
命名实体识别（Named Entity Recognition，NER）中的“命名实体”一般是指文本中具有特别意义或指代性非常强的实体（比如：人名，地名，时间或者机构组织等）。命名实体可分为实体类、时间类和数字类3大类，以及人名、机构名、地名、时间、日期、货币和百分比7小类。命名实体识别在NLP中占有重要地位，它是信息提取、机器翻译和问答系统等应用领域里的基础工具。命名实体识别的任务就是识别出文本中的命名实体，通常分为实体边界识别和实体类别识别两个过程。
人工智能-命名实体识别-中文-CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity
07-03
命名实体识别（Named Entity Recognition, NER）是自然语言处理（Natural Language Processing, NLP）领域的一个关键任务，它涉及到从文本中识别出具有特定意义的实体，如人名、地名、组织名等。在“人工智能-命名...
NLP（自然语言处理）命名实体识别代码详细步骤示例
08-15
### NLP（自然语言处理）命名实体识别代码详细步骤示例 #### 一、环境与工具介绍 在本文中，我们将详细介绍如何使用Python中的spaCy库进行命名实体识别（Named Entity Recognition, NER）。spaCy是一款强大的开源...
CCKS2019中文命名实体识别任务.zip
07-02
【标题】"CCKS2019中文命名实体识别任务.zip" 提供的是一个针对中文文本的命名实体识别（NER）任务，该任务在2019年CCKS（China Conference on Knowledge Graph and Semantic Computing）大会上进行。CCKS是中国在...
使用bert预训练模型微调实现命名实体识别任务
03-11
### 使用BERT预训练模型微调实现命名实体识别任务 #### 一、背景介绍与理论基础 **命名实体识别（Named Entity Recognition, NER）**是自然语言处理领域的一项关键技术，其目的是从文本中识别出具有特定意义的实体...
基于华为云的命名实体识别实验指导书1
08-03
命名实体识别（Named Entity Recognition, NER）是自然语言处理（Natural Language Processing, NLP）领域的一个关键任务，它的目标是从文本中识别出具有特定意义的实体，如人名、地名、组织名等，并对这些实体进行...
中文命名实体识别
09-18
主要是用来处理中文的命名实体识别，主要是用tensorflow
处理好的人民日报语料，可以直接用CRF训练命名实体
06-05
处理好的人民日报语料，用于命名实体识别，两个文件分别为字符集和词语级
中文命名实体识别语料（MSRA+人民日报+Boson）
11-11
适合作为命名实体识别的补充预料，包括微软亚研院MSRA：46365条语料、人民日报：23061条语料和Boson:2000条语料。都是标注过的，非常实用，适合新手作为刚开始的模型练习。
nlp_ner:使用Bi-LSTM和crf来进行人名识别，数据集人民日报98年1月标注数据集，训练：验证：测试为3：1：1
04-29
nlp_ner 使用Bi-LSTM和crf来进行人名识别，数据集人民日报98年1月标注数据集，训练：验证：测试为3：1：1 数据说明 原数据文件是/data/rmrb199801.txt data_process.py对文件进行了大量的处理 结果 acc：0.99 f1：0.9
命名实体识别（Named Entity Recognition，NER）
victoriaGYR的博客
12-13 3818
  命名实体识别（Named Entity Recognition，NER）属于NLP中一个关键性基础任务，概念从字面意思上就可以理解，即识别文本中具有特定意义的实体，主要包括人名、地名、机构名、专有名词等。    从早期基于词典和规则的方法，到传统机器学习的方法，到近年来基于深度学习的方法，NER研究进展的大概趋势大致如下图所示。   在基于机器学习的方法中，NER被当作序列标注问题。利...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值