基于Bert的情感多分类任务(超高精度)

上传者: Ye_meng_li | 上传时间: 2022-04-20 09:07:02 | 文件大小: 223.76MB | 文件类型: ZIP
运行记录: 训练集每类9k数据集,训练集一般为每类1k; 1.利用英文数据集进行二分类,因为数据可能过于中和,运行正确率在85%左右,其中测试集没有label输出自己评价可以发现测试集正确率和验证集类似,大约85%,epoch为2 2.利用上述影评二分类,label 0 1 对应1 5星影评,正确率在99%+ 3.利用上述影评三分类,label 0 1 2对应1 3 5星影评,正确率在99%左右 4.利用上述影评四分类,label 0 1 2 3对应1 3 4 5星影评,小数据训练,135星各9k训练集,4星10个训练集,输出相同大小,准确率78%左右,也就是说基本预测错误,说明不可以进行小规模训练。 5.利用上述影评五分类,label 0 1 2 3 4对应1 2 3 4 5星影评,正确率97%+

文件下载

资源详情

[{"title":"( 21 个子文件 223.76MB ) 基于Bert的情感多分类任务(超高精度)","children":[{"title":"情感分析","children":[{"title":"Readme.txt <span style='color:#111;'> 5.04KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"test1.csv <span style='color:#111;'> 549.04KB </span>","children":null,"spread":false},{"title":"1.csv <span style='color:#111;'> 700.52KB </span>","children":null,"spread":false},{"title":"5.csv <span style='color:#111;'> 323.74KB </span>","children":null,"spread":false},{"title":"3.csv <span style='color:#111;'> 392.47KB </span>","children":null,"spread":false},{"title":"4.csv <span style='color:#111;'> 349.89KB </span>","children":null,"spread":false},{"title":"筛选.py <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"ratings.zip <span style='color:#111;'> 104.99MB </span>","children":null,"spread":false},{"title":"test5.csv <span style='color:#111;'> 495.99KB </span>","children":null,"spread":false},{"title":"ratings","children":[{"title":"ratings.csv <span style='color:#111;'> 269.68MB </span>","children":null,"spread":false},{"title":"movies.csv <span style='color:#111;'> 959B </span>","children":null,"spread":false}],"spread":true},{"title":"test2.csv <span style='color:#111;'> 1.23MB </span>","children":null,"spread":false},{"title":"test3.csv <span style='color:#111;'> 668.72KB </span>","children":null,"spread":false},{"title":"2.csv <span style='color:#111;'> 920.84KB </span>","children":null,"spread":false},{"title":"test4.csv <span style='color:#111;'> 534.26KB </span>","children":null,"spread":false}],"spread":false},{"title":"英文data","children":[{"title":"noncomplaint1700.csv <span style='color:#111;'> 221.32KB </span>","children":null,"spread":false},{"title":"test_data.csv <span style='color:#111;'> 772.12KB </span>","children":null,"spread":false},{"title":"complaint1700.csv <span style='color:#111;'> 227.94KB </span>","children":null,"spread":false}],"spread":true},{"title":"Bert分类.py <span style='color:#111;'> 14.68KB </span>","children":null,"spread":false},{"title":"References.txt <span style='color:#111;'> 1.75KB </span>","children":null,"spread":false},{"title":"训练集验证结果.png <span style='color:#111;'> 159.59KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

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