如何找出不直接出现在句子中的基于关键词的相似句子？

from transformers import BertTokenizer, BertModel
import torch
import numpy as np

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

def get_bert_embedding(text):
    inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)
    outputs = model(**inputs)
    return outputs.last_hidden_state.mean(dim=1).detach().numpy()

def cosine_similarity(vec1, vec2):
    return np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2))

# 示例文本
text1 = "How to find similar sentences based on keywords?"
text2 = "Methods for detecting semantically similar phrases."

# 获取BERT嵌入
embedding1 = get_bert_embedding(text1)
embedding2 = get_bert_embedding(text2)

# 计算相似度
similarity = cosine_similarity(embedding1, embedding2)
print(f"Similarity: {similarity}")