Python计算文本余弦相似度

最新推荐文章于 2024-08-30 21:46:36 发布

Deeachain

最新推荐文章于 2024-08-30 21:46:36 发布

阅读量2.5k

点赞数

分类专栏： Python

本文链接：https://blog.csdn.net/Deeachain/article/details/106981160

版权

#!/usr/bin/python3
import kashgari
from kashgari.embeddings import BERTEmbedding
import logging
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
import jieba
import sys

chinese_bert_file='./data/chinese_L-12_H-768_A-12'

def cal_cosine():
    bert = BERTEmbedding(chinese_bert_file,
                            task=kashgari.CLASSIFICATION,
                            sequence_length=10)

    # call for single embed
    sen1 = input('sentence1:')
    sen2 = input('sentence2:') 

    seg_list1 = jieba.cut(sen1, cut_all=False)
    seg_list2 = jieba.cut(sen2, cut_all=False)
    
    seg_list1 = list(seg_list1)
    seg_list2 = list(seg_list2)
    embed_tensor1 = bert.embed_one(seg_list1)
    embed_tensor2 = bert.embed_one(seg_list2)

    embedding1 = np.zeros(shape=(1,3072))
    embedding2 = np.zeros(shape=(1,3072))
    
    for i in range(embed_tensor1.shape[0