BertSimilarity:使用Google的BERT算法计算两个句子的相似度。利用Bert计算句子相似度。语义相似度计算-源码

上传者: 42099755 | 上传时间: 2021-08-24 18:33:00 | 文件大小: 2.82MB | 文件类型: ZIP
伯特相似度 基于Google的BERT模型来进行语义相似度计算。代码基于tensorflow 1。 1.基本原理 简单来说就是将需要需要计算的相似性的两个句子先分解在一起,然后通过伯特模型获取获取整体的编码信息,然后通过全连接层将维,输出相似和不相似的概率。 1.1模型结构 模型结构所示如下: 1.1.1数据预处理 本文使用Bert模型计算相似度前,首先要对输入数据进行预处理,例如当要处理的文本是: 如何得知关闭借呗 想永久关闭借呗 首先进行文本按token化,切成分割的文字排列: [如 何 得 知 关 闭 借 呗] [想 永 久 关 闭 借 呗] 然后将两个切分后的句子,按照如下的方式

文件下载

资源详情

[{"title":"( 26 个子文件 2.82MB ) BertSimilarity:使用Google的BERT算法计算两个句子的相似度。利用Bert计算句子相似度。语义相似度计算-源码","children":[{"title":"BertSimilarity-master","children":[{"title":"similarity.py <span style='color:#111;'> 28.63KB </span>","children":null,"spread":false},{"title":"tokenization.py <span style='color:#111;'> 10.31KB </span>","children":null,"spread":false},{"title":"logs","children":[{"title":"train.log <span style='color:#111;'> 64.10KB </span>","children":null,"spread":false},{"title":"loss.log <span style='color:#111;'> 874B </span>","children":null,"spread":false}],"spread":true},{"title":"shell","children":[{"title":"extract_log.sh <span style='color:#111;'> 111B </span>","children":null,"spread":false}],"spread":true},{"title":"data","children":[{"title":"dataset","children":[{"title":"train.csv <span style='color:#111;'> 5.54MB </span>","children":null,"spread":false},{"title":"dev.csv <span style='color:#111;'> 2.58MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"visilize.py <span style='color:#111;'> 622B </span>","children":null,"spread":false},{"title":"wiki","children":[{"title":"pictures","children":[{"title":"similarity_eval_1.png <span style='color:#111;'> 54.28KB </span>","children":null,"spread":false},{"title":"similarity_eualtion_1.png <span style='color:#111;'> 1.46KB </span>","children":null,"spread":false},{"title":"similarity_train.png <span style='color:#111;'> 25.01KB </span>","children":null,"spread":false},{"title":"bert_embedding.png <span style='color:#111;'> 65.66KB </span>","children":null,"spread":false},{"title":"similarity_infer.png <span style='color:#111;'> 40.31KB </span>","children":null,"spread":false},{"title":"similarity_bert_model.png <span style='color:#111;'> 14.28KB </span>","children":null,"spread":false},{"title":"similarity_eval.png <span style='color:#111;'> 21.56KB </span>","children":null,"spread":false},{"title":"similarity_data_process.png <span style='color:#111;'> 17.22KB </span>","children":null,"spread":false},{"title":"bert_similarity.png <span style='color:#111;'> 128.70KB </span>","children":null,"spread":false}],"spread":true},{"title":"diagram","children":[{"title":"bert_similarity.drawio <span style='color:#111;'> 3.44KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 616B </span>","children":null,"spread":false},{"title":"args.py <span style='color:#111;'> 781B </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 31B </span>","children":null,"spread":false},{"title":"optimization.py <span style='color:#111;'> 5.90KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 92B </span>","children":null,"spread":false},{"title":"start.sh <span style='color:#111;'> 635B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 5.54KB </span>","children":null,"spread":false},{"title":"modeling.py <span style='color:#111;'> 37.19KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

  • weixin_42318736 :
    用户下载后在一定时间内未进行评价,系统默认好评。
    2021-08-07

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明