KBQA_zh:基于BERT的KBQA，包含joint和pipeline两种模式
KBQA_zh
基于bert的KBQA，包含joint和pipeline两种模式
Introduction
本项目是一个基于知识三元组的简单的问答系统，分为joint和pipeline两种模式。joint模式为基于bert做意图识别和命名体识别的联合学习训练得到的模型，pipeline模式为单独训练命名实体识别和QA相似度模型。
Environment
tensorflow 1.15
python 3.6
pymysql 0.10.1
grpcio 1.32.0
grpcio-tools 1.32.0
How to run
首先需要下载bert的中文预训练模型放在chinese_L-12_H-768_A-12文件夹下，
然后，以pipeline模式为例，执行如下命令，训练命名实体识别模型和问答模型：
1. cd qa_pipeline
2. sh run_ner.sh
3. sh run_
文件下载
资源详情
[{"title":"（ 66 个子文件 4.68MB ） KBQA_zh:基于BERT的KBQA，包含joint和pipeline两种模式","children":[{"title":"KBQA_zh-master","children":[{"title":"README.md <span style='color:#111;'> 2.19KB </span>","children":null,"spread":false},{"title":"bert","children":[{"title":"predicting_movie_reviews_with_bert_on_tf_hub.ipynb <span style='color:#111;'> 64.93KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.33KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 49.33KB </span>","children":null,"spread":false},{"title":"tokenization.py <span style='color:#111;'> 11.97KB </span>","children":null,"spread":false},{"title":"optimization.py <span style='color:#111;'> 6.11KB </span>","children":null,"spread":false},{"title":"run_squad.py <span style='color:#111;'> 45.44KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"multilingual.md <span style='color:#111;'> 10.98KB </span>","children":null,"spread":false},{"title":"modeling_test.py <span style='color:#111;'> 8.98KB </span>","children":null,"spread":false},{"title":"CONTRIBUTING.md <span style='color:#111;'> 1.29KB </span>","children":null,"spread":false},{"title":"create_pretraining_data.py <span style='color:#111;'> 16.09KB </span>","children":null,"spread":false},{"title":"tokenization_test.py <span style='color:#111;'> 4.48KB </span>","children":null,"spread":false},{"title":"optimization_test.py <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"sample_text.txt <span style='color:#111;'> 4.29KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 616B </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 110B </span>","children":null,"spread":false},{"title":"run_classifier.py <span style='color:#111;'> 34.00KB </span>","children":null,"spread":false},{"title":"run_classifier_with_tfhub.py <span style='color:#111;'> 11.16KB </span>","children":null,"spread":false},{"title":"extract_features.py <span style='color:#111;'> 13.57KB </span>","children":null,"spread":false},{"title":"run_pretraining.py <span style='color:#111;'> 18.23KB </span>","children":null,"spread":false},{"title":"modeling.py <span style='color:#111;'> 37.03KB </span>","children":null,"spread":false}],"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"qa_joint","children":[{"title":"qa_joint_pb2_grpc.py <span style='color:#111;'> 2.24KB </span>","children":null,"spread":false},{"title":"joint_module.py <span style='color:#111;'> 8.78KB </span>","children":null,"spread":false},{"title":"run_joint.sh <span style='color:#111;'> 518B </span>","children":null,"spread":false},{"title":"joint_classifier.py <span style='color:#111;'> 33.61KB </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 5.18KB </span>","children":null,"spread":false},{"title":"qa_joint_client.py <span style='color:#111;'> 1.83KB </span>","children":null,"spread":false},{"title":"qa_joint_pb2.py <span style='color:#111;'> 4.07KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"metrics.cpython-36.pyc <span style='color:#111;'> 4.73KB </span>","children":null,"spread":false},{"title":"qa_joint_pb2.cpython-36.pyc <span style='color:#111;'> 2.39KB </span>","children":null,"spread":false},{"title":"joint_module.cpython-36.pyc <span style='color:#111;'> 6.42KB </span>","children":null,"spread":false}],"spread":true},{"title":"qa_joint.proto <span style='color:#111;'> 533B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"JOINT_Data","children":[{"title":"test.tsv <span style='color:#111;'> 1.13MB </span>","children":null,"spread":false},{"title":"train.tsv <span style='color:#111;'> 1.64MB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"qa_joint_server.py <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false}],"spread":false},{"title":"emo.png <span style='color:#111;'> 266.12KB </span>","children":null,"spread":false},{"title":"qa_pipeline","children":[{"title":"ner_module.py <span style='color:#111;'> 7.37KB </span>","children":null,"spread":false},{"title":"chinese_ner.py <span style='color:#111;'> 27.94KB </span>","children":null,"spread":false},{"title":"run_qa.sh <span style='color:#111;'> 497B </span>","children":null,"spread":false},{"title":"qa_pipeline_pb2_grpc.py <span style='color:#111;'> 2.27KB </span>","children":null,"spread":false},{"title":"qa_server.py <span style='color:#111;'> 901B </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 5.18KB </span>","children":null,"spread":false},{"title":"qa_pipeline_pb2.py <span style='color:#111;'> 4.12KB </span>","children":null,"spread":false},{"title":"run_ner.sh <span style='color:#111;'> 502B </span>","children":null,"spread":false},{"title":"qa_system.py <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"metrics.cpython-36.pyc <span style='color:#111;'> 4.72KB </span>","children":null,"spread":false},{"title":"qa_pipeline_pb2.cpython-36.pyc <span style='color:#111;'> 2.43KB </span>","children":null,"spread":false},{"title":"ner_module.cpython-36.pyc <span style='color:#111;'> 5.46KB </span>","children":null,"spread":false},{"title":"qa_system.cpython-36.pyc <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false},{"title":"chinese_ner.cpython-36.pyc <span style='color:#111;'> 19.88KB </span>","children":null,"spread":false},{"title":"qa_pipeline_pb2_grpc.cpython-36.pyc <span style='color:#111;'> 2.32KB </span>","children":null,"spread":false},{"title":"qa_module.cpython-36.pyc <span style='color:#111;'> 4.61KB </span>","children":null,"spread":false},{"title":"chinese_qa.cpython-36.pyc <span style='color:#111;'> 19.23KB </span>","children":null,"spread":false}],"spread":false},{"title":"qa_module.py <span style='color:#111;'> 6.49KB </span>","children":null,"spread":false},{"title":"qa_client.py <span style='color:#111;'> 1.86KB </span>","children":null,"spread":false},{"title":"qa_pipeline.proto <span style='color:#111;'> 536B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"NER_Data","children":[{"title":"test.tsv <span style='color:#111;'> 906.77KB </span>","children":null,"spread":false},{"title":"train.tsv <span style='color:#111;'> 1.28MB </span>","children":null,"spread":false}],"spread":false},{"title":"DB_Data","children":[{"title":"test.tsv <span style='color:#111;'> 2.84MB </span>","children":null,"spread":false},{"title":"train.tsv <span style='color:#111;'> 4.01MB </span>","children":null,"spread":false}],"spread":false},{"title":"kbqa.kb <span style='color:#111;'> 29.15KB </span>","children":null,"spread":false}],"spread":false},{"title":"chinese_qa.py <span style='color:#111;'> 27.76KB </span>","children":null,"spread":false}],"spread":false},{"title":"chinese_L-12_H-768_A-12","children":[{"title":"readme.md <span style='color:#111;'> 98B </span>","children":null,"spread":false}],"spread":true},{"title":"KGMySql.py <span style='color:#111;'> 719B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- c++旅行售货员问题源代码
- 人工智能(模糊算法)
- Origin 9.0 科技绘图与数据分析超级学习手册，完整扫描版
- 软件质量保证与测试2012第一版秦航清华大学出版社.pdf-其它文档类资源
- 自己封装的epoll事件驱动模型
- 信息安全风险评估与风险管理.ppt
- usft_Auto_SysForeignKeyIndex.sql
- 印制电路板（PCB）设计技术与实践 第3版.rar
- c#中使用委托按升序和降序对一组随机生成的整型数组元素进行排序
- AlarmManagerDemo(含 广播, service , activity的demo)
- 使用Authorware制作复杂多媒体课件简单教程(内含4个实例，外付一个实验报告（详细）)一
- s3c2440 bsp for vxworks
- 获取本地计算机信息 NetHelper.cs
- 扩展程序：R锈蚀扩展库，旨在使R用户熟悉-源码
- Linux系统软件安装方法.mp4
- awesome-fuse：精选的Fuse应用程序，文章和插件的精选列表-源码
- Android之常用命令和工具
- windows 32位 CMake3.3.txt
- 《电子测量技术基础》(张永瑞第三版)第2章测量误差和测量误差处理.pdf
- 多语种网络硬盘系统的设计论文
- Android更换头像功能
- sqljdbc41.jar
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