Pinned Repositories
Chid_Bert_baseline
A based-bert baseline for Chinese idiom cloze test with pytorch.
Crawl
Use multi-threaded crawler to crawl the idiom data
Crosswoz_nlu_task
利用中文大规模对话数据集Crosswoz,进行NLU任务实验。
Educational_system
教务管理系统javaweb项目 运行环境:window系统,Apache Tomcat v7.0.84、JDK1.8 开发环境:J2EE eclipse、navicat for mysql 运用的技术:MVC设计模式、DAO模式、Servlet、JSP、Filter、MySQL数据库 该项目主要分为登录系统,学生,教师,教务员,系统管理员四大部分,实现了登录,找回密码,修改密码,注销,学生用户的成绩查询,选修与考级报名、学籍信息的查看与修改与考级成绩的查询;教师用户的个人信息查询与修改; 教务员用户的成绩管理,个人信息查询与修改、选修与考级报名学生名单管理员用户对用户的管理。 javaweb的初学者可以下载下来参考学习。下载回来后首先看README.txt文件,帮助理解,启动系统。 系统还有一些功能待实现,可以继续添加完善其他功能与新功能
es_search
python class for elasticsearch , including add, batch add, update, delete, query, and scan query. also with a demo that put Wikipedia into elasticsearch and query by keywords or sentence.
NCPQA
Datafountain-Epidemic government affairs quiz assistant competition. We divided this task into two parts: document retrieval and answer extraction. pytorch, Albert, and model fuision
NLP_Chinese_data_Augment
中文数据增强封装类:同义词替换、随机插入、随机交换、随机删除
NLPEngine
这是通用的NLP任务训练框架,基于pytorch和transformers框架搭建。
semantic-similarity
semantic similarity, word2vec + wmd, bert+wmd, pytorch
tf-idf
tf-idf 模型封装类,包含计算所有文档的tf-idf值,实现了基于tf-idf搜索引擎功能。根据query,计算与每个文档的相似度,返回与query相似度最高的topk文档
Tanh-wink's Repositories
Tanh-wink/Educational_system
教务管理系统javaweb项目 运行环境:window系统,Apache Tomcat v7.0.84、JDK1.8 开发环境:J2EE eclipse、navicat for mysql 运用的技术:MVC设计模式、DAO模式、Servlet、JSP、Filter、MySQL数据库 该项目主要分为登录系统,学生,教师,教务员,系统管理员四大部分,实现了登录,找回密码,修改密码,注销,学生用户的成绩查询,选修与考级报名、学籍信息的查看与修改与考级成绩的查询;教师用户的个人信息查询与修改; 教务员用户的成绩管理,个人信息查询与修改、选修与考级报名学生名单管理员用户对用户的管理。 javaweb的初学者可以下载下来参考学习。下载回来后首先看README.txt文件,帮助理解,启动系统。 系统还有一些功能待实现,可以继续添加完善其他功能与新功能
Tanh-wink/semantic-similarity
semantic similarity, word2vec + wmd, bert+wmd, pytorch
Tanh-wink/Chid_Bert_baseline
A based-bert baseline for Chinese idiom cloze test with pytorch.
Tanh-wink/es_search
python class for elasticsearch , including add, batch add, update, delete, query, and scan query. also with a demo that put Wikipedia into elasticsearch and query by keywords or sentence.
Tanh-wink/tf-idf
tf-idf 模型封装类,包含计算所有文档的tf-idf值,实现了基于tf-idf搜索引擎功能。根据query,计算与每个文档的相似度,返回与query相似度最高的topk文档
Tanh-wink/Crawl
Use multi-threaded crawler to crawl the idiom data
Tanh-wink/NCPQA
Datafountain-Epidemic government affairs quiz assistant competition. We divided this task into two parts: document retrieval and answer extraction. pytorch, Albert, and model fuision
Tanh-wink/NLP_Chinese_data_Augment
中文数据增强封装类:同义词替换、随机插入、随机交换、随机删除
Tanh-wink/NLPEngine
这是通用的NLP任务训练框架,基于pytorch和transformers框架搭建。
Tanh-wink/Crosswoz_nlu_task
利用中文大规模对话数据集Crosswoz,进行NLU任务实验。
Tanh-wink/data_augment
NLP的数据增强Demo
Tanh-wink/question_generator
2020 Tianchi TCM Question Generation Competition, bert4keras, 2020年天池中医药问题生成竞赛
Tanh-wink/Angle_predict
A regression task with LSTM or GRU for angle predict
Tanh-wink/Audio_segment
Audio segmentation by classification
Tanh-wink/awesome_LLMs_interview_notes
LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案
Tanh-wink/ccks2021-track2-code
“英特尔创新大师杯”深度学习挑战赛 赛道2:CCKS2021中文NLP地址要素解析
Tanh-wink/CLUENER2020
A PyTorch implementation of a BiLSTM\BERT\Roberta(+CRF) model for Named Entity Recognition.
Tanh-wink/DataCompetitionBaseline
Tanh-wink/go_service
go gin; 日志采集logger,异常处理,统计耗时,企业微信告警,请求参数验证
Tanh-wink/goutils
Tanh-wink/GraphEmbedding
Implementation and experiments of graph embedding algorithms.
Tanh-wink/Harlen520.github.io
Tanh-wink/HomePage-1
Yunhe Wang's HomePage
Tanh-wink/KBQA-BERT
基于知识图谱的问答系统,BERT做命名实体识别和句子相似度,分为online和outline模式
Tanh-wink/matplotlib_mac_chinese
mac在matplotlib中显示中文的操作方法
Tanh-wink/neural_dependency_parser
neural dependency parser in pytorch
Tanh-wink/question_matching
question matching, paddlepaddle
Tanh-wink/stop-words
List of common stop words in various languages.
Tanh-wink/Tanh-cv
Maintain your CV in Markdown :sparkles:
Tanh-wink/Tanh-wink.github.io