BERT实体关系联合抽取Python代码

下面是一个简单的BERT实体关系联合抽取的Python代码示例：

import torch
import transformers
import numpy as np

# 加载预训练的BERT模型和分词器
tokenizer = transformers.BertTokenizer.from_pretrained('bert-base-uncased')
model = transformers.BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

# 定义实体关系类别
labels = ['NO_RELATIONSHIP', 'RELATIONSHIP']

# 定义样本句子和实体位置
text = "The company Apple was founded by Steve Jobs and Steve Wozniak."
entity1 = (4, 9, 'Apple')
entity2 = (32, 42, 'Steve Jobs')

# 对样本进行分词和编码
encoded_dict = tokenizer.encode_plus(
                    text,
                    text_pair=None,
                    add_special_tokens=True,
                    truncation_strategy='longest_first',
                    max_length=128,
                    padding='max_length',
                    return_attention_mask=True,
                    return_tensors='pt'
               )

# 获取实体位置的相对编码位置
entity1_start = np.where(encoded_dict['input_ids'] == tokenizer.encode(entity1[2], add_special_tokens=False)[0])[0][0]
entity1_end = entity1_start + len(tokenizer.encode(entity1[2], add_special_tokens=False)) - 1
entity2_start = np.where(encoded_dict['input_ids'] == tokenizer.encode(entity2[2], add_special_tokens=False)[0])[0][0]
entity2_end = entity2_start + len(tokenizer.encode(entity2[2], add_special_tokens=False)) - 1

# 构造输入张量
input_ids = encoded_dict['input_ids']
attention_mask = encoded_dict['attention_mask']
token_type_ids = encoded_dict['token_type_ids']
entity1_mask = [0] * len(input_ids)
for i in range(entity1_start, entity1_end + 1):
    entity1_mask[i] = 1
entity2_mask = [0] * len(input_ids)
for i in range(entity2_start, entity2_end + 1):
    entity2_mask[i] = 1

# 转换为PyTorch张量
input_ids = torch.tensor(input_ids).unsqueeze(0)
attention_mask = torch.tensor(attention_mask).unsqueeze(0)
token_type_ids = torch.tensor(token_type_ids).unsqueeze(0)
entity1_mask = torch.tensor(entity1_mask).unsqueeze(0)
entity2_mask = torch.tensor(entity2_mask).unsqueeze(0)

# 前向传播
outputs = model(
    input_ids=input_ids,
    attention_mask=attention_mask,
    token_type_ids=token_type_ids,
    labels=None,
    entity1_mask=entity1_mask,
    entity2_mask=entity2_mask
)

# 预测实体关系类别
logits = outputs[0]
_, predicted = torch.max(logits, 1)
relationship = labels[predicted.item()]

print("实体1：", entity1[2])
print("实体2：", entity2[2])
print("实体关系：", relationship)

需要注意的是，上述代码仅供参考，具体实现可能因数据集、模型和任务不同而有所变化。