Dureader-Bert：BERT Dureader多文档阅读理解排名第七-源码
Dureader-Bert
2019 Dureader机器阅读理解单模型代码。
哈工大讯飞联合实验室发布的中文全词覆盖BERT
只需将要加载的预训练模型换为压缩包内的chinese_wwm_pytorch.bin，即从_pretrained函数中weights_path和config_file即可。
谷歌发布的中文伯特与哈工大发布的中文全词覆盖BERT在Dureader上的效果对比
模型
ROUGE-L
BLEU-4
谷歌bert
49.3
50.2
哈工大伯特
50.32
51.4
由于官方没有指定测试集，实验数据是在验证集上跑出来的
许多人询问，说明一下：
1，数据处理是自己写
文件下载
资源详情
[{"title":"（ 76 个子文件 86.97MB ） Dureader-Bert：BERT Dureader多文档阅读理解排名第七-源码","children":[{"title":"Dureader-Bert-master","children":[{"title":"Dureader","children":[{"title":"train.py <span style='color:#111;'> 2.78KB </span>","children":null,"spread":false},{"title":"predict","children":[{"title":"file_utils.py <span style='color:#111;'> 7.72KB </span>","children":null,"spread":false},{"title":"util.py <span style='color:#111;'> 2.30KB </span>","children":null,"spread":false},{"title":"predict_data.py <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false},{"title":"predict.data <span style='color:#111;'> 15.39MB </span>","children":null,"spread":false},{"title":"tokenization.py <span style='color:#111;'> 14.22KB </span>","children":null,"spread":false},{"title":"modeling.py <span style='color:#111;'> 53.40KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"modeling.cpython-35.pyc <span style='color:#111;'> 49.92KB </span>","children":null,"spread":false},{"title":"tokenization.cpython-35.pyc <span style='color:#111;'> 11.92KB </span>","children":null,"spread":false},{"title":"args.cpython-35.pyc <span style='color:#111;'> 890B </span>","children":null,"spread":false},{"title":"file_utils.cpython-35.pyc <span style='color:#111;'> 6.74KB </span>","children":null,"spread":false},{"title":"predict_data.cpython-35.pyc <span style='color:#111;'> 1006B </span>","children":null,"spread":false}],"spread":true},{"title":"args.py <span style='color:#111;'> 851B </span>","children":null,"spread":false},{"title":"predicting.py <span style='color:#111;'> 4.85KB </span>","children":null,"spread":false}],"spread":true},{"title":"optimizer.py <span style='color:#111;'> 7.08KB </span>","children":null,"spread":false},{"title":".idea","children":[{"title":"misc.xml <span style='color:#111;'> 292B </span>","children":null,"spread":false},{"title":"workspace.xml <span style='color:#111;'> 12.56KB </span>","children":null,"spread":false},{"title":"Dureader.iml <span style='color:#111;'> 729B </span>","children":null,"spread":false},{"title":"modules.xml <span style='color:#111;'> 268B </span>","children":null,"spread":false},{"title":"fileColors.xml <span style='color:#111;'> 169B </span>","children":null,"spread":false}],"spread":true},{"title":"dataset","children":[{"title":"file_utils.py <span style='color:#111;'> 7.72KB </span>","children":null,"spread":false},{"title":"run_squad.py <span style='color:#111;'> 8.05KB </span>","children":null,"spread":false},{"title":"tokenization.py <span style='color:#111;'> 14.22KB </span>","children":null,"spread":false},{"title":"dataloader.py <span style='color:#111;'> 1.39KB </span>","children":null,"spread":false},{"title":"train.data <span style='color:#111;'> 4.82MB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"dev.data <span style='color:#111;'> 4.56MB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"__init__.cpython-35.pyc <span style='color:#111;'> 120B </span>","children":null,"spread":false},{"title":"tokenization.cpython-35.pyc <span style='color:#111;'> 11.91KB </span>","children":null,"spread":false},{"title":"dataloader.cpython-35.pyc <span style='color:#111;'> 1.73KB </span>","children":null,"spread":false},{"title":"args.cpython-35.pyc <span style='color:#111;'> 890B </span>","children":null,"spread":false},{"title":"file_utils.cpython-35.pyc <span style='color:#111;'> 6.74KB </span>","children":null,"spread":false}],"spread":false},{"title":"args.py <span style='color:#111;'> 851B </span>","children":null,"spread":false}],"spread":true},{"title":"handle_data","children":[{"title":"run.sh <span style='color:#111;'> 1.66KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"preprocess.cpython-35.pyc <span style='color:#111;'> 5.30KB </span>","children":null,"spread":false}],"spread":true},{"title":"paragraph_extraction.py <span style='color:#111;'> 7.52KB </span>","children":null,"spread":false},{"title":"preprocess.pyc <span style='color:#111;'> 5.63KB </span>","children":null,"spread":false},{"title":"preprocess.py <span style='color:#111;'> 6.92KB </span>","children":null,"spread":false}],"spread":true},{"title":"metric","children":[{"title":".vimrc <span style='color:#111;'> 98B </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 216B </span>","children":null,"spread":false},{"title":"bleu.py <span style='color:#111;'> 3.71KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"mrc_eval.cpython-35.pyc <span style='color:#111;'> 5.70KB </span>","children":null,"spread":false},{"title":"common.cpython-35.pyc <span style='color:#111;'> 1.53KB </span>","children":null,"spread":false},{"title":"rouge.cpython-35.pyc <span style='color:#111;'> 2.63KB </span>","children":null,"spread":false},{"title":"bleu.cpython-35.pyc <span style='color:#111;'> 3.91KB </span>","children":null,"spread":false}],"spread":true},{"title":"e.data <span style='color:#111;'> 3.87KB </span>","children":null,"spread":false},{"title":"rouge.py <span style='color:#111;'> 2.60KB </span>","children":null,"spread":false},{"title":"mrc_eval.py <span style='color:#111;'> 7.21KB </span>","children":null,"spread":false},{"title":"common.py <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"model_dir","children":[{"title":"bert_config.json <span style='color:#111;'> 504B </span>","children":null,"spread":false},{"title":"modeling.py <span style='color:#111;'> 53.41KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"__init__.cpython-35.pyc <span style='color:#111;'> 122B </span>","children":null,"spread":false},{"title":"modeling.cpython-35.pyc <span style='color:#111;'> 49.89KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"__pycache__","children":[{"title":"evaluate.cpython-35.pyc <span style='color:#111;'> 921B </span>","children":null,"spread":false},{"title":"args.cpython-35.pyc <span style='color:#111;'> 882B </span>","children":null,"spread":false},{"title":"optimizer.cpython-35.pyc <span style='color:#111;'> 5.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"args.py <span style='color:#111;'> 876B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"trainset","children":[{"title":"zhidao.train.json <span style='color:#111;'> 33.50MB </span>","children":null,"spread":false},{"title":"search.train.json <span style='color:#111;'> 35.35MB </span>","children":null,"spread":false}],"spread":true},{"title":"devset","children":[{"title":"zhidao.dev.json <span style='color:#111;'> 33.50MB </span>","children":null,"spread":false},{"title":"search.dev.json <span style='color:#111;'> 35.35MB </span>","children":null,"spread":false}],"spread":false},{"title":"testset","children":[{"title":"zhidao.test1.json <span style='color:#111;'> 33.50MB </span>","children":null,"spread":false},{"title":"search.test1.json <span style='color:#111;'> 35.35MB </span>","children":null,"spread":false}],"spread":false},{"title":"extracted","children":[{"title":"trainset","children":[{"title":"zhidao.train.json <span style='color:#111;'> 27.44MB </span>","children":null,"spread":false},{"title":"search.train.json <span style='color:#111;'> 23.15MB </span>","children":null,"spread":false}],"spread":false},{"title":"devset","children":[{"title":"zhidao.dev.json <span style='color:#111;'> 27.35MB </span>","children":null,"spread":false},{"title":"search.dev.json <span style='color:#111;'> 22.97MB </span>","children":null,"spread":false}],"spread":false},{"title":"testset","children":[{"title":"zhidao.test1.json <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"search.test1.json <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true},{"title":"evaluate.py <span style='color:#111;'> 851B </span>","children":null,"spread":false}],"spread":false},{"title":"1.png <span style='color:#111;'> 50.28KB </span>","children":null,"spread":false},{"title":"2.png <span style='color:#111;'> 105.24KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.49KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- 康奈尔电影对话语料库
- 多点温度采集系统+Proteus仿真
- Qt使用QMediaPlayer制作的视频播放器
- Android 评论、回复功能，测试demo
- 矩阵论（第三版）程云鹏pdf电子书
- 生物信息学算法导论（an-introduction-to-bioinformatics-algorithms）
- cudart64_101.dll
- Model predictive control of a mobile robot using linearization
- java学习从入门到精通
- CL_IT_004_V1.0 发布管理办法.docx
- 基于VC++ 摄影测量计算程序
- MATLAB源码集锦-小波神经网络的时间序列预测代码
- 火狐浏览器安卓公测版86.0.0-beta3_armv7a
- JaspersoftStudio（2017-zv）.rar
- terraform-provider-lxd：用于Terraform的LXD资源提供程序-源码
- EPM570 CPLD PCI接口开发板AD设计硬件原理图+PCB+封装库文件.zip
- GECOOS_AXR3100_IPQ40XX_6.3_2020122100.bin
- EXCEL_VBA制作员工考勤系统源码
- LINGO10.zip
- 戴尔（DELL）服务器 PREC S130 RD卡驱动
- graphics.h(vs使用的图形头文件)
- UltraEdit、UltraCompare激活工具
- 天猫淘宝秒杀抢购插件源码
- 基于Proteus的单片机RS232与RS485应用案例
- python3抓百度贴吧帖子源码
- NSGA-II matlab程序+by Aravind Seshadri
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
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