René's URL Explorer Experiment

Title: GitHub - pudongdong/NLP_ability: 总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力 · GitHub

Open Graph Title: GitHub - pudongdong/NLP_ability: 总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

X Title: GitHub - pudongdong/NLP_ability: 总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

Description: 总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力 - pudongdong/NLP_ability

Open Graph Description: 总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力 - pudongdong/NLP_ability

X Description: 总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力 - pudongdong/NLP_ability

Opengraph URL: https://github.com/pudongdong/NLP_ability

X: @github

direct link

Domain: github.com

route-pattern	/:user_id/:repository
route-controller	files
route-action	disambiguate
fetch-nonce	v2:ab41d3cc-6a30-4e1c-fdae-822fe68a50ac
current-catalog-service-hash	f3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-id	C4A4:AF1E5:1F59A7:2C6D24:6A4BB1E6
html-safe-nonce	d7df5d1fff55e4b5ab3f612a2d129ef31111274c74c0cc534ab660fa3ea2a596
visitor-payload	eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJDNEE0OkFGMUU1OjFGNTlBNzoyQzZEMjQ6NkE0QkIxRTYiLCJ2aXNpdG9yX2lkIjoiMjQ1ODkzMjU4MDQ4MjUyNzcxOCIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9
visitor-hmac	ad287321f441e7ee846ab7fb55177ac13ecfdb1e0d692b1597b8bf3f7ff47de0
hovercard-subject-tag	repository:420694849
github-keyboard-shortcuts	repository,copilot
google-site-verification	Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-url	https://collector.github.com/github/collect
analytics-location	//
fb:app_id	1401488693436528
apple-itunes-app	app-id=1477376905, app-argument=https://github.com/pudongdong/NLP_ability
twitter:image	https://opengraph.githubassets.com/83f2689c0ba8f27bf2b9f5cfbc1f9431e35e6adb35d5411cf630fe6239297b18/pudongdong/NLP_ability
twitter:card	summary_large_image
og:image	https://opengraph.githubassets.com/83f2689c0ba8f27bf2b9f5cfbc1f9431e35e6adb35d5411cf630fe6239297b18/pudongdong/NLP_ability
og:image:alt	总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力 - pudongdong/NLP_ability
og:image:width	1200
og:image:height	600
og:site_name	GitHub
og:type	object
hostname	github.com
expected-hostname	github.com
None	3ede370c1d797b0693475db9bb4298020548dcae9c98a2f071d54aaf1b4e9faa
turbo-cache-control	no-cache
go-import	github.com/pudongdong/NLP_ability git https://github.com/pudongdong/NLP_ability.git
octolytics-dimension-user_id	23382349
octolytics-dimension-user_login	pudongdong
octolytics-dimension-repository_id	420694849
octolytics-dimension-repository_nwo	pudongdong/NLP_ability
octolytics-dimension-repository_public	true
octolytics-dimension-repository_is_fork	true
octolytics-dimension-repository_parent_id	272599346
octolytics-dimension-repository_parent_nwo	DA-southampton/NLP_ability
octolytics-dimension-repository_network_root_id	272599346
octolytics-dimension-repository_network_root_nwo	DA-southampton/NLP_ability
turbo-body-classes	logged-out env-production page-responsive
disable-turbo	false
browser-stats-url	https://api.github.com/_private/browser/stats
browser-errors-url	https://api.github.com/_private/browser/errors
release	af627ba2b0ed5351c6d1b8e04fdbe893325c237f
ui-target	full
theme-color	#1e2327
color-scheme	light dark

Links:

Skip to content	https://github.com/pudongdong/NLP_ability#start-of-content
	https://github.com/
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fpudongdong%2FNLP_ability
GitHub CopilotWrite better code with AI	https://github.com/features/copilot
GitHub Copilot appDirect agents from issue to merge	https://github.com/features/ai/github-app
MCP RegistryNewIntegrate external tools	https://github.com/mcp
ActionsAutomate any workflow	https://github.com/features/actions
CodespacesInstant dev environments	https://github.com/features/codespaces
IssuesPlan and track work	https://github.com/features/issues
Code ReviewManage code changes	https://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilities	https://github.com/security/advanced-security
Code securitySecure your code as you build	https://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they start	https://github.com/security/advanced-security/secret-protection
Why GitHub	https://github.com/why-github
Documentation	https://docs.github.com
Blog	https://github.blog
Changelog	https://github.blog/changelog
Marketplace	https://github.com/marketplace
View all features	https://github.com/features
Enterprises	https://github.com/enterprise
Small and medium teams	https://github.com/team
Startups	https://github.com/enterprise/startups
Nonprofits	https://github.com/solutions/industry/nonprofits
App Modernization	https://github.com/solutions/use-case/app-modernization
DevSecOps	https://github.com/solutions/use-case/devsecops
DevOps	https://github.com/solutions/use-case/devops
CI/CD	https://github.com/solutions/use-case/ci-cd
View all use cases	https://github.com/solutions/use-case
Healthcare	https://github.com/solutions/industry/healthcare
Financial services	https://github.com/solutions/industry/financial-services
Manufacturing	https://github.com/solutions/industry/manufacturing
Government	https://github.com/solutions/industry/government
View all industries	https://github.com/solutions/industry
View all solutions	https://github.com/solutions
AI	https://github.com/resources/articles?topic=ai
Software Development	https://github.com/resources/articles?topic=software-development
DevOps	https://github.com/resources/articles?topic=devops
Security	https://github.com/resources/articles?topic=security
View all topics	https://github.com/resources/articles
Customer stories	https://github.com/customer-stories
Events & webinars	https://github.com/resources/events
Ebooks & reports	https://github.com/resources/whitepapers
Business insights	https://github.com/solutions/executive-insights
GitHub Skills	https://skills.github.com
Documentation	https://docs.github.com
Customer support	https://support.github.com
Community forum	https://github.com/orgs/community/discussions
Trust center	https://github.com/trust-center
Partners	https://github.com/partners
View all resources	https://github.com/resources
GitHub SponsorsFund open source developers	https://github.com/sponsors
Security Lab	https://securitylab.github.com
Maintainer Community	https://maintainers.github.com
Accelerator	https://github.com/accelerator
GitHub Stars	https://stars.github.com
Archive Program	https://archiveprogram.github.com
Topics	https://github.com/topics
Trending	https://github.com/trending
Collections	https://github.com/collections
Enterprise platformAI-powered developer platform	https://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security features	https://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI features	https://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 support	https://github.com/premium-support
Pricing	https://github.com/pricing
Search syntax tips	https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentation	https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fpudongdong%2FNLP_ability
Sign up	https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=pudongdong%2FNLP_ability
Reload	https://github.com/pudongdong/NLP_ability
Reload	https://github.com/pudongdong/NLP_ability
Reload	https://github.com/pudongdong/NLP_ability
pudongdong	https://github.com/pudongdong
NLP_ability	https://github.com/pudongdong/NLP_ability
DA-southampton/NLP_ability	https://github.com/DA-southampton/NLP_ability
Notifications	https://github.com/login?return_to=%2Fpudongdong%2FNLP_ability
Fork 1	https://github.com/login?return_to=%2Fpudongdong%2FNLP_ability
Star 0	https://github.com/login?return_to=%2Fpudongdong%2FNLP_ability
Code	https://github.com/pudongdong/NLP_ability
Pull requests 0	https://github.com/pudongdong/NLP_ability/pulls
Actions	https://github.com/pudongdong/NLP_ability/actions
Projects	https://github.com/pudongdong/NLP_ability/projects
Security and quality 0	https://github.com/pudongdong/NLP_ability/security
Insights	https://github.com/pudongdong/NLP_ability/pulse
Code	https://github.com/pudongdong/NLP_ability
Pull requests	https://github.com/pudongdong/NLP_ability/pulls
Actions	https://github.com/pudongdong/NLP_ability/actions
Projects	https://github.com/pudongdong/NLP_ability/projects
Security and quality	https://github.com/pudongdong/NLP_ability/security
Insights	https://github.com/pudongdong/NLP_ability/pulse
	https://github.com/pudongdong/NLP_ability
Branches	https://github.com/pudongdong/NLP_ability/branches
Tags	https://github.com/pudongdong/NLP_ability/tags
	https://github.com/pudongdong/NLP_ability/branches
	https://github.com/pudongdong/NLP_ability/tags
233 Commits	https://github.com/pudongdong/NLP_ability/commits/master/
	https://github.com/pudongdong/NLP_ability/commits/master/
Pytorch	https://github.com/pudongdong/NLP_ability/tree/master/Pytorch
Pytorch	https://github.com/pudongdong/NLP_ability/tree/master/Pytorch
推荐	https://github.com/pudongdong/NLP_ability/tree/master/%E6%8E%A8%E8%8D%90
推荐	https://github.com/pudongdong/NLP_ability/tree/master/%E6%8E%A8%E8%8D%90
搜索	https://github.com/pudongdong/NLP_ability/tree/master/%E6%90%9C%E7%B4%A2
搜索	https://github.com/pudongdong/NLP_ability/tree/master/%E6%90%9C%E7%B4%A2
机器学习	https://github.com/pudongdong/NLP_ability/tree/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0
机器学习	https://github.com/pudongdong/NLP_ability/tree/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0
模型部署	https://github.com/pudongdong/NLP_ability/tree/master/%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2
模型部署	https://github.com/pudongdong/NLP_ability/tree/master/%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2
深度学习自然语言处理	https://github.com/pudongdong/NLP_ability/tree/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86
深度学习自然语言处理	https://github.com/pudongdong/NLP_ability/tree/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86
计算机基础知识	https://github.com/pudongdong/NLP_ability/tree/master/%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%9F%BA%E7%A1%80%E7%9F%A5%E8%AF%86
计算机基础知识	https://github.com/pudongdong/NLP_ability/tree/master/%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%9F%BA%E7%A1%80%E7%9F%A5%E8%AF%86
.DS_Store	https://github.com/pudongdong/NLP_ability/blob/master/.DS_Store
.DS_Store	https://github.com/pudongdong/NLP_ability/blob/master/.DS_Store
README.md	https://github.com/pudongdong/NLP_ability/blob/master/README.md
README.md	https://github.com/pudongdong/NLP_ability/blob/master/README.md
README_OLD.md	https://github.com/pudongdong/NLP_ability/blob/master/README_OLD.md
README_OLD.md	https://github.com/pudongdong/NLP_ability/blob/master/README_OLD.md
README	https://github.com/pudongdong/NLP_ability
	https://github.com/pudongdong/NLP_ability#背景介绍
B站主页-NLP学习之路	https://space.bilibili.com/414678948
	https://camo.githubusercontent.com/467222115c3884650f74516f6dcdcc4ed3d27468fb08ec73c996940ffb96a30f/68747470733a2f2f70696373666f726461626c6f672e6f73732d636e2d6265696a696e672e616c6979756e63732e636f6d2f323032302d31322d32322d3034313835352e6a7067
	https://github.com/pudongdong/NLP_ability#深度学习自然语言处理
	https://github.com/pudongdong/NLP_ability#transformer
史上最全Transformer面试题	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/%E5%8F%B2%E4%B8%8A%E6%9C%80%E5%85%A8Transformer%E9%9D%A2%E8%AF%95%E9%A2%98.md
答案解析(1)-史上最全Transformer面试题	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/%E7%AD%94%E6%A1%88%E8%A7%A3%E6%9E%90(1)%E2%80%94%E5%8F%B2%E4%B8%8A%E6%9C%80%E5%85%A8Transformer%E9%9D%A2%E8%AF%95%E9%A2%98%EF%BC%9A%E7%81%B5%E9%AD%8220%E9%97%AE%E5%B8%AE%E4%BD%A0%E5%BD%BB%E5%BA%95%E6%90%9E%E5%AE%9ATransformer.md
Pytorch代码分析--如何让Bert在finetune小数据集时更“稳”一点	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/Pytorch%E4%BB%A3%E7%A0%81%E5%88%86%E6%9E%90-%E5%A6%82%E4%BD%95%E8%AE%A9Bert%E5%9C%A8finetune%E5%B0%8F%E6%95%B0%E6%8D%AE%E9%9B%86%E6%97%B6%E6%9B%B4%E2%80%9C%E7%A8%B3%E2%80%9D%E4%B8%80%E7%82%B9.md
解决老大难问题-如何一行代码带你随心所欲重新初始化bert的某些参数(附Pytorch代码详细解读)	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/%E8%A7%A3%E5%86%B3%E8%80%81%E5%A4%A7%E9%9A%BE%E9%97%AE%E9%A2%98-%E5%A6%82%E4%BD%95%E4%B8%80%E8%A1%8C%E4%BB%A3%E7%A0%81%E5%B8%A6%E4%BD%A0%E9%9A%8F%E5%BF%83%E6%89%80%E6%AC%B2%E9%87%8D%E6%96%B0%E5%88%9D%E5%A7%8B%E5%8C%96bert%E7%9A%84%E6%9F%90%E4%BA%9B%E5%8F%82%E6%95%B0(%E9%99%84Pytorch%E4%BB%A3%E7%A0%81).md
3分钟从零解读Transformer的Encoder	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/3%E5%88%86%E9%92%9F%E4%BB%8E%E9%9B%B6%E8%A7%A3%E8%AF%BBTransformer%E7%9A%84Encoder.md
原版Transformer的位置编码究竟有没有包含相对位置信息	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/%E5%8E%9F%E7%89%88Transformer%E7%9A%84%E4%BD%8D%E7%BD%AE%E7%BC%96%E7%A0%81%E7%A9%B6%E7%AB%9F%E6%9C%89%E6%B2%A1%E6%9C%89%E5%8C%85%E5%90%AB%E7%9B%B8%E5%AF%B9%E4%BD%8D%E7%BD%AE%E4%BF%A1%E6%81%AF.md
BN踩坑记--谈一下Batch Normalization的优缺点和适用场景	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/BN%E8%B8%A9%E5%9D%91%E8%AE%B0--%E8%B0%88%E4%B8%80%E4%B8%8BBatch%20Normalization%E7%9A%84%E4%BC%98%E7%BC%BA%E7%82%B9%E5%92%8C%E9%80%82%E7%94%A8%E5%9C%BA%E6%99%AF.md
谈一下相对位置编码	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/%E8%B0%88%E4%B8%80%E4%B8%8B%E7%9B%B8%E5%AF%B9%E4%BD%8D%E7%BD%AE%E7%BC%96%E7%A0%81.md
NLP任务中-layer-norm比BatchNorm好在哪里	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/NLP%E4%BB%BB%E5%8A%A1%E4%B8%AD-layer-norm%E6%AF%94BatchNorm%E5%A5%BD%E5%9C%A8%E5%93%AA%E9%87%8C.md
谈一谈Decoder模块	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/%E8%B0%88%E4%B8%80%E8%B0%88Decoder%E6%A8%A1%E5%9D%97.md
Transformer的并行化	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/Transformer%E7%9A%84%E5%B9%B6%E8%A1%8C%E5%8C%96.md
Transformer全部文章合辑	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/%E7%AD%94%E6%A1%88%E5%90%88%E8%BE%91.md
RNN的梯度消失有什么与众不同的地方.md	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%85%B6%E4%BB%96/RNN%E7%9A%84%E6%A2%AF%E5%BA%A6%E6%B6%88%E5%A4%B1%E6%9C%89%E4%BB%80%E4%B9%88%E4%B8%8E%E4%BC%97%E4%B8%8D%E5%90%8C%E7%9A%84%E5%9C%B0%E6%96%B9.md
VIT-如何将Transformer更好的应用到CV领域	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Transformer/VIT-%E5%A6%82%E4%BD%95%E5%B0%86Transformer%E6%9B%B4%E5%A5%BD%E7%9A%84%E5%BA%94%E7%94%A8%E5%88%B0CV%E9%A2%86%E5%9F%9F.md
	https://github.com/pudongdong/NLP_ability#bert-基本知识
FastBERT-CPU推理加速10倍	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/FastBert.md
Bert如何融入知识(一)-百度和清华ERINE	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/Bert%E5%A6%82%E4%BD%95%E8%9E%8D%E5%85%A5%E7%9F%A5%E8%AF%86%E4%B8%80-%E7%99%BE%E5%BA%A6%E5%92%8C%E6%B8%85%E5%8D%8EERINE.md
Bert如何融入知识二-Bert融合知识图谱	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/Bert%E5%A6%82%E4%BD%95%E8%9E%8D%E5%85%A5%E7%9F%A5%E8%AF%86%E4%BA%8C-Bert%E8%9E%8D%E5%90%88%E7%9F%A5%E8%AF%86%E5%9B%BE%E8%B0%B1.md
Bert的可视化-Bert每一层都学到了什么	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/Bert%E7%9A%84%E5%8F%AF%E8%A7%86%E5%8C%96-Bert%E6%AF%8F%E4%B8%80%E5%B1%82%E9%83%BD%E5%AD%A6%E5%88%B0%E4%BA%86%E4%BB%80%E4%B9%88.md
Bert各种后续预训练模型-预训练模型的改进	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/Bert%E5%90%84%E7%A7%8D%E5%90%8E%E7%BB%AD%E9%A2%84%E8%AE%AD%E7%BB%83%E6%A8%A1%E5%9E%8B-%E9%A2%84%E8%AE%AD%E7%BB%83%E6%A8%A1%E5%9E%8B%E7%9A%84%E6%94%B9%E8%BF%9B.md
RoBERTa：更多更大更强	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/RoBERTa.md
为什么Bert做不好无监督语义匹配	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/%E4%B8%BA%E4%BB%80%E4%B9%88Bert%E5%81%9A%E4%B8%8D%E5%A5%BD%E6%97%A0%E7%9B%91%E7%9D%A3%E8%AF%AD%E4%B9%89%E5%8C%B9%E9%85%8D.md
UniLM:为Bert插上文本生成的翅膀	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/UniLM.md
tBERT-BERT融合主题模型做文本匹配	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/tBERT-BERT%E8%9E%8D%E5%90%88%E4%B8%BB%E9%A2%98%E6%A8%A1%E5%9E%8B.md
XLNET	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/Bert/XLNET.md
如何在脱敏数据中使用BERT等预训练模型	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A6%82%E4%BD%95%E5%9C%A8%E8%84%B1%E6%95%8F%E6%95%B0%E6%8D%AE%E4%B8%AD%E4%BD%BF%E7%94%A8BERT%E7%AD%89%E9%A2%84%E8%AE%AD%E7%BB%83%E6%A8%A1%E5%9E%8B.md
	https://github.com/pudongdong/NLP_ability#bert-知识蒸馏
什么是知识蒸馏	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/%E4%BB%80%E4%B9%88%E6%98%AF%E7%9F%A5%E8%AF%86%E8%92%B8%E9%A6%8F.md
如何让 TextCNN 逼近 Bert	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/bert2textcnn%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F.md
Bert蒸馏到简单网络lstm	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/Bert%E8%92%B8%E9%A6%8F%E5%88%B0%E7%AE%80%E5%8D%95%E7%BD%91%E7%BB%9Clstm.md
PKD-Bert基于多层的知识蒸馏方式	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/PKD-Bert%E5%9F%BA%E4%BA%8E%E5%A4%9A%E5%B1%82%E7%9A%84%E7%9F%A5%E8%AF%86%E8%92%B8%E9%A6%8F%E6%96%B9%E5%BC%8F.md
BERT-of-Theseus-模块压缩交替训练	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/Theseus-%E6%A8%A1%E5%9D%97%E5%8E%8B%E7%BC%A9%E4%BA%A4%E6%9B%BF%E8%AE%AD%E7%BB%83.md
tinybert-全方位蒸馏	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/tinybert-%E5%85%A8%E6%96%B9%E4%BD%8D%E8%92%B8%E9%A6%8F.md
ALBERT：更小更少但并不快	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/ALBERT-%E6%9B%B4%E5%B0%8F%E6%9B%B4%E5%B0%91%E4%BD%86%E5%B9%B6%E4%B8%8D%E5%BF%AB.md
BERT知识蒸馏代码解析-如何写好损失函数	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%A8%A1%E5%9E%8B%E8%92%B8%E9%A6%8F/BERT%E7%9F%A5%E8%AF%86%E8%92%B8%E9%A6%8F%E4%BB%A3%E7%A0%81%E8%A7%A3%E6%9E%90-%E5%A6%82%E4%BD%95%E5%86%99%E5%A5%BD%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0.md
	https://github.com/pudongdong/NLP_ability#词向量-word-embedding
史上最全词向量面试题-Word2vec/fasttext/glove/Elmo	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/%E5%8F%B2%E4%B8%8A%E6%9C%80%E5%85%A8%E8%AF%8D%E5%90%91%E9%87%8F%E9%9D%A2%E8%AF%95%E9%A2%98%E6%A2%B3%E7%90%86.md
Word2vec两种训练模型详细解读-一个词经过模型训练可以获得几个词向量	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/%E8%81%8A%E4%B8%80%E4%B8%8BWord2vec-%E6%A8%A1%E5%9E%8B%E7%AF%87.md
Word2vec两种优化方式细节详细解读	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/%E8%81%8A%E4%B8%80%E4%B8%8BWord2vec-%E8%AE%AD%E7%BB%83%E4%BC%98%E5%8C%96%E7%AF%87.md
Word2vec-负采样和层序softmax与原模型是否等价	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/word2vec%E4%B8%A4%E7%A7%8D%E4%BC%98%E5%8C%96%E6%96%B9%E5%BC%8F%E7%9A%84%E8%81%94%E7%B3%BB%E5%92%8C%E5%8C%BA%E5%88%AB.md
Word2vec为何需要二次采样以及相关细节详细解读	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/Word2vec%E4%B8%BA%E4%BB%80%E4%B9%88%E9%9C%80%E8%A6%81%E4%BA%8C%E6%AC%A1%E9%87%87%E6%A0%B7%EF%BC%9F.md
Word2vec的负采样	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/Word2vec%E7%9A%84%E8%B4%9F%E9%87%87%E6%A0%B7.md
Word2vec模型究竟是如何获得词向量的	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/Word2vec%E6%A8%A1%E5%9E%8B%E7%A9%B6%E7%AB%9F%E6%98%AF%E5%A6%82%E4%BD%95%E8%8E%B7%E5%BE%97%E8%AF%8D%E5%90%91%E9%87%8F%E7%9A%84.md
Word2vec训练参数的选定	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/Word2vec%E8%AE%AD%E7%BB%83%E5%8F%82%E6%95%B0%E7%9A%84%E9%80%89%E5%AE%9A.md
CBOW和skip-gram相较而言，彼此相对适合哪些场景.md	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/CBOW%E5%92%8Cskip-gram%E7%9B%B8%E8%BE%83%E8%80%8C%E8%A8%80%EF%BC%8C%E5%BD%BC%E6%AD%A4%E7%9B%B8%E5%AF%B9%E9%80%82%E5%90%88%E5%93%AA%E4%BA%9B%E5%9C%BA%E6%99%AF.md
Fasttext详解解读(1)-文本分类	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/Fasttext%E8%A7%A3%E8%AF%BB(1).md
Fasttext详解解读(2)-训练词向量	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/Fasttext%E8%A7%A3%E8%AF%BB(2).md
GLove细节详细解读	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E8%AF%8D%E5%90%91%E9%87%8F/%E8%81%8A%E4%B8%80%E4%B8%8BGlove.md
	https://github.com/pudongdong/NLP_ability#多模态
多模态之ViLBERT：双流网络，各自为王	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E5%A4%9A%E6%A8%A1%E6%80%81%E4%B9%8BViLBERT%EF%BC%9A%E5%8F%8C%E6%B5%81%E7%BD%91%E7%BB%9C%EF%BC%8C%E5%90%84%E8%87%AA%E4%B8%BA%E7%8E%8B.md
复盘多模态需要解决的6个问题	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E5%A4%8D%E7%9B%98%E5%A4%9A%E6%A8%A1%E6%80%81%E9%9C%80%E8%A6%81%E8%A7%A3%E5%86%B3%E7%9A%846%E4%B8%AA%E9%97%AE%E9%A2%98.md
如何将多模态数据融入到BERT架构中-多模态BERT的两类预训练任务	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E5%A6%82%E4%BD%95%E5%B0%86%E5%A4%9A%E6%A8%A1%E6%80%81%E6%95%B0%E6%8D%AE%E8%9E%8D%E5%85%A5%E5%88%B0BERT%E6%9E%B6%E6%9E%84%E4%B8%AD-%E5%A4%9A%E6%A8%A1%E6%80%81BERT%E7%9A%84%E4%B8%A4%E7%B1%BB%E9%A2%84%E8%AE%AD%E7%BB%83%E4%BB%BB%E5%8A%A1.md
层次分类体系的必要性-多模态讲解系列(1)	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E5%B1%82%E6%AC%A1%E5%88%86%E7%B1%BB%E4%BD%93%E7%B3%BB%E7%9A%84%E5%BF%85%E8%A6%81%E6%80%A7-%E5%A4%9A%E6%A8%A1%E6%80%81%E8%AE%B2%E8%A7%A3%E7%B3%BB%E5%88%97.md
文本和图像特征表示模块详解-多模态讲解系列(2)	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E6%96%87%E6%9C%AC%E5%92%8C%E5%9B%BE%E5%83%8F%E7%89%B9%E5%BE%81%E8%A1%A8%E7%A4%BA%E6%A8%A1%E5%9D%97%E8%AF%A6%E8%A7%A3-%E5%A4%9A%E6%A8%A1%E6%80%81%E8%AE%B2%E8%A7%A3%E7%B3%BB%E5%88%97.md
层次体系具体是如何构建的-多模态讲解系列(3)	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E5%B1%82%E6%AC%A1%E4%BD%93%E7%B3%BB%E7%9A%84%E6%9E%84%E5%BB%BA-%E5%A4%9A%E6%A8%A1%E6%80%81%E8%A7%A3%E6%9E%90.md
多模态中各种Fusion方式汇总	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%A4%9A%E6%A8%A1%E6%80%81/%E5%A4%9A%E6%A8%A1%E6%80%81%E4%B8%AD%E5%90%84%E7%A7%8DFusion%E6%96%B9%E5%BC%8F%E6%B1%87%E6%80%BB.md
	https://github.com/pudongdong/NLP_ability#句向量-sentence-embedding
句向量模型综述	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%8F%A5%E5%90%91%E9%87%8F/%E5%8F%A5%E5%90%91%E9%87%8F%E6%A8%A1%E5%9E%8B%E7%BB%BC%E8%BF%B0.md
	https://github.com/pudongdong/NLP_ability#文本相似度
五千字全面梳理文本相似度/文本匹配模型	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/%E4%BA%94%E5%8D%83%E5%AD%97%E5%85%A8%E9%9D%A2%E6%A2%B3%E7%90%86%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E5%92%8C%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E6%A8%A1%E5%9E%8B.md
如何又好又快的做文本匹配-ESIM模型	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/ESIM.md
阿里RE2-将残差连接和文本匹配模型融合.md	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/%E9%98%BF%E9%87%8CRE2-%E5%B0%86%E6%AE%8B%E5%B7%AE%E8%BF%9E%E6%8E%A5%E5%92%8C%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E6%A8%A1%E5%9E%8B%E8%9E%8D%E5%90%88.md
聊一下孪生网络和DSSM的混淆点以及向量召回的一个细节	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/%E8%81%8A%E4%B8%80%E4%B8%8B%E5%AD%AA%E7%94%9F%E7%BD%91%E7%BB%9C%E5%92%8CDSSM%E7%9A%84%E6%B7%B7%E6%B7%86%E7%82%B9%E4%BB%A5%E5%8F%8A%E5%90%91%E9%87%8F%E5%8F%AC%E5%9B%9E%E7%9A%84%E4%B8%80%E4%B8%AA%E7%BB%86%E8%8A%82.md
DSSM论文-公司实战文章	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/DSSM%E8%AE%BA%E6%96%87-%E5%85%AC%E5%8F%B8%E5%AE%9E%E6%88%98%E6%96%87%E7%AB%A0.md
bert白化简单的梳理:公式推导+PCA&SVD+代码解读	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/bert%E7%99%BD%E5%8C%96%E7%AE%80%E5%8D%95%E7%9A%84%E6%A2%B3%E7%90%86.md
SIMCSE论文解析	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%8C%B9%E9%85%8D%E5%92%8C%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6/SIMCSE%E8%AE%BA%E6%96%87%E8%A7%A3%E6%9E%90.md
	https://github.com/pudongdong/NLP_ability#关键词提取
基于词典的正向/逆向最大匹配	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%85%B3%E9%94%AE%E8%AF%8D%E6%8F%90%E5%8F%96/%E4%B8%AD%E6%96%87%E5%88%86%E8%AF%8D/%E5%9F%BA%E4%BA%8E%E8%AF%8D%E5%85%B8%E7%9A%84%E6%AD%A3%E5%90%91%E6%9C%80%E5%A4%A7%E5%8C%B9%E9%85%8D%E5%92%8C%E9%80%86%E5%90%91%E6%9C%80%E5%A4%A7%E5%8C%B9%E9%85%8D%E4%B8%AD%E6%96%87%E5%88%86%E8%AF%8D.md
实体库构建：大规模离线新词实体挖掘	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%85%B3%E9%94%AE%E8%AF%8D%E6%8F%90%E5%8F%96/%E5%AE%9E%E4%BD%93%E5%BA%93%E6%9E%84%E5%BB%BA%EF%BC%9A%E5%A4%A7%E8%A7%84%E6%A8%A1%E7%A6%BB%E7%BA%BF%E6%96%B0%E8%AF%8D%E5%AE%9E%E4%BD%93%E6%8C%96%E6%8E%98.md
聊一聊NLPer如何做关键词抽取	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%85%B3%E9%94%AE%E8%AF%8D%E6%8F%90%E5%8F%96/%E5%85%B3%E9%94%AE%E8%AF%8D%E6%8F%90%E5%8F%96%E6%96%B9%E6%B3%95%E7%BB%BC%E8%BF%B0.md
	https://github.com/pudongdong/NLP_ability#命名体识别
命名体识别资源梳理(代码+博客讲解)	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB%E8%B5%84%E6%BA%90%E6%A2%B3%E7%90%86(%E4%BB%A3%E7%A0%81%2B%E5%8D%9A%E5%AE%A2%E8%AE%B2%E8%A7%A3).md
HMM/CRF 详细解读	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/HMM_CRF.md
工业级命名体识别的做法	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/%E5%B7%A5%E4%B8%9A%E7%BA%A7%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB%E7%9A%84%E5%81%9A%E6%B3%95.md
词典匹配+模型预测-实体识别两大法宝	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/%E8%AF%8D%E5%85%B8%E5%8C%B9%E9%85%8D%2B%E6%A8%A1%E5%9E%8B%E9%A2%84%E6%B5%8B-%E5%AE%9E%E4%BD%93%E8%AF%86%E5%88%AB%E4%B8%A4%E5%A4%A7%E6%B3%95%E5%AE%9D.md
autoner+fuzzy-CRF-使用领域词典做命名体识别	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/autoner.md
FLAT-Transformer-词典+Transformer融合词汇信息	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/FLAT-Transformer.md
TENER-复旦为什么TRM在NER上效果差.md	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%91%BD%E5%90%8D%E4%BD%93%E8%AF%86%E5%88%AB/TNER-%E5%A4%8D%E6%97%A6%E4%B8%BA%E4%BB%80%E4%B9%88TRM%E5%9C%A8NER%E4%B8%8A%E6%95%88%E6%9E%9C%E5%B7%AE.md
	https://github.com/pudongdong/NLP_ability#文本分类
TextCNN论文详细解读	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/CNN%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB%E8%A7%A3%E8%AF%BB.md
只使用标签名称就可以文本分类.md	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/%E5%8F%AA%E4%BD%BF%E7%94%A8%E6%A0%87%E7%AD%BE%E5%90%8D%E7%A7%B0%E5%B0%B1%E5%8F%AF%E4%BB%A5%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB.md
半监督入门思想之伪标签	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/%E5%8D%8A%E7%9B%91%E7%9D%A3%E5%85%A5%E9%97%A8%E6%80%9D%E6%83%B3%E4%B9%8B%E4%BC%AA%E6%A0%87%E7%AD%BE.md
ACL2020-多任务负监督方式增加CLS表达差异性	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/ACL2020-%E5%A4%9A%E4%BB%BB%E5%8A%A1%E8%B4%9F%E7%9B%91%E7%9D%A3%E6%96%B9%E5%BC%8F%E5%A2%9E%E5%8A%A0CLS%E8%A1%A8%E8%BE%BE%E5%B7%AE%E5%BC%82%E6%80%A7.md
Bert在文本分类任务上微调	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/%E5%9C%A8%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB%E4%B8%8A%E5%BE%AE%E8%B0%83Bert.md
UDA-Unsupervised Data Augmentation for Consistency Training-半监督集大成	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/UDA.md
LCM-缓解标签不独立以及标注错误的问题	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/LCM-%E7%BC%93%E8%A7%A3%E6%A0%87%E7%AD%BE%E4%B8%8D%E7%8B%AC%E7%AB%8B%E4%BB%A5%E5%8F%8A%E6%A0%87%E6%B3%A8%E9%94%99%E8%AF%AF%E7%9A%84%E9%97%AE%E9%A2%98.md
关键词信息如何融入到文本分类任务中	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB/%E5%85%B3%E9%94%AE%E8%AF%8D%E4%BF%A1%E6%81%AF%E5%A6%82%E4%BD%95%E8%9E%8D%E5%85%A5%E5%88%B0%E6%96%87%E6%9C%AC%E5%88%86%E7%B1%BB%E4%BB%BB%E5%8A%A1%E4%B8%AD.md
	https://github.com/pudongdong/NLP_ability#机器翻译
OpenNMT源代码解读(pytorch版)-baseline操作OpenNMT-py	https://github.com/DA-southampton/NLP_ability/tree/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%9C%BA%E5%99%A8%E7%BF%BB%E8%AF%91/OpenNMT-py
BPE论文解读	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E6%9C%BA%E5%99%A8%E7%BF%BB%E8%AF%91/bpe-subword%E8%AE%BA%E6%96%87%E7%9A%84%E6%88%91%E7%9A%84%E9%98%85%E8%AF%BB%E6%80%BB%E7%BB%93.md
	https://github.com/pudongdong/NLP_ability#pytorch
pytorch对text数据的预处理-综述	https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%AF%B9text%E6%95%B0%E6%8D%AE%E7%9A%84%E9%A2%84%E5%A4%84%E7%90%86-%E7%BB%BC%E8%BF%B0.md
pytorch处理文本数据代码版本1-处理文本相似度数据	https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC1-%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%95%B0%E6%8D%AE.md
pytorch处理文本数据代码版本2-处理文本相似度数据	https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC2-%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%95%B0%E6%8D%AE.md
Pytorch中mask attention是如何实现的代码版本1-阅读文本相似度模型的小总结	https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/Pytorch%E4%B8%ADmask%E6%98%AF%E5%A6%82%E4%BD%95%E5%AE%9E%E7%8E%B0%E7%9A%84%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC1-%E9%98%85%E8%AF%BB%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%A8%A1%E5%9E%8B.md
验证集loss上升，准确率却上升该如何理解？	https://www.zhihu.com/question/318399418
	https://github.com/pudongdong/NLP_ability#机器学习
真实场景如何解决类别不平衡的问题	https://github.com/pudongdong/NLP_ability/blob/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/%E7%9C%9F%E5%AE%9E%E5%9C%BA%E6%99%AF%E5%A6%82%E4%BD%95%E8%A7%A3%E5%86%B3%E7%B1%BB%E5%88%AB%E4%B8%8D%E5%B9%B3%E8%A1%A1%E7%9A%84%E9%97%AE%E9%A2%98.md
特征工程-数据探索	https://github.com/pudongdong/NLP_ability/blob/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/%E5%B7%A5%E4%B8%9A%E8%92%B8%E6%B1%BD%E9%A2%84%E6%B5%8B/%E7%89%B9%E5%BE%81%E5%B7%A5%E7%A8%8B-%E6%95%B0%E6%8D%AE%E6%8E%A2%E7%B4%A2.md
xgboost全面解析	https://github.com/pudongdong/NLP_ability/blob/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/xgboost/xgboost.md
xgboost完整训练代码	https://github.com/pudongdong/NLP_ability/blob/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/xgboost/xgboost%E8%AE%AD%E7%BB%83%E4%BB%A3%E7%A0%81.py
xgboost特征重要程度代码	https://github.com/pudongdong/NLP_ability/blob/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/xgboost/xgboost%E8%8E%B7%E5%BE%97%E7%89%B9%E5%BE%81%E9%87%8D%E8%A6%81%E7%A8%8B%E5%BA%A6%E5%B9%B6%E7%94%BB%E5%9B%BE.py
	https://github.com/pudongdong/NLP_ability#搜索
各种关于搜索的好文章资源总结-看到比较不错的就放上来	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%90%9C%E7%B4%A2/%E6%90%9C%E7%B4%A2%E8%B5%84%E6%BA%90%E6%80%BB%E7%BB%93-%E6%8C%81%E7%BB%AD%E6%9B%B4%E6%96%B0.md
什么是倒排索引	https://github.com/pudongdong/NLP_ability/blob/master/%E6%90%9C%E7%B4%A2/%E5%80%92%E6%8E%92%E7%B4%A2%E5%BC%95%E5%9F%BA%E6%9C%AC%E6%A6%82%E5%BF%B5.md
	https://github.com/pudongdong/NLP_ability#推荐系统
聊一下Wide&Deep	https://github.com/pudongdong/NLP_ability/blob/master/%E6%8E%A8%E8%8D%90/WDL/WDl.md
WDL 在贝壳推荐场景的实践	https://github.com/pudongdong/NLP_ability/blob/master/%E6%8E%A8%E8%8D%90/WDL/WDL%E5%9C%A8%E8%B4%9D%E5%A3%B3%E4%B8%AD%E7%9A%84%E5%BA%94%E7%94%A8%E5%AE%9E%E8%B7%B5%E6%80%BB%E7%BB%93.md
FM模型简单介绍	https://github.com/pudongdong/NLP_ability/blob/master/%E6%8E%A8%E8%8D%90/FM.md
DeepFM模型简单介绍	https://github.com/pudongdong/NLP_ability/blob/master/%E6%8E%A8%E8%8D%90/deepfm.md
各种关于推荐的好文章资源总结-看到比较不错的就放上来	https://github.com/DA-southampton/NLP_ability/blob/master/%E6%8E%A8%E8%8D%90/%E6%8E%A8%E8%8D%90%E8%B5%84%E6%BA%90%E6%9B%B4%E6%96%B0.md
度学习在推荐系统中的应用	https://mp.weixin.qq.com/s?__biz=MzI1NjM1ODEyMg==&mid=2247484656&idx=1&sn=35845ab0839807a314d6e500d9384bf1&chksm=ea26a775dd512e63ec800bf4f0d162e421531776ca86c0147ae7711b2541bfe87ecfb6104169&scene=21#wechat_redirect
推荐系统特征构建	https://zhuanlan.zhihu.com/p/221783604
推荐系统特征工程的万字理论	https://cloud.tencent.com/developer/article/1574246
新商品类别embedding如何动态更新-增量更新embedding	https://zhuanlan.zhihu.com/p/77789278
	https://github.com/pudongdong/NLP_ability#公众号技术问题答疑汇总
20201210一周\|技术问题答疑汇总	https://github.com/pudongdong/NLP_ability/blob/master/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86/%E5%85%B6%E4%BB%96/20201210%E4%B8%80%E5%91%A8%7C%E6%8A%80%E6%9C%AF%E9%97%AE%E9%A2%98%E7%AD%94%E7%96%91%E6%B1%87%E6%80%BB.md
	https://github.com/pudongdong/NLP_ability#模型部署
算法工程师常说的【处理数据】究竟是在做什么	https://github.com/pudongdong/NLP_ability/blob/master/%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2/%E7%AE%97%E6%B3%95%E5%B7%A5%E7%A8%8B%E5%B8%88%E5%B8%B8%E8%AF%B4%E7%9A%84%5B%E5%A4%84%E7%90%86%E6%95%B0%E6%8D%AE%5D%E7%A9%B6%E7%AB%9F%E6%98%AF%E5%9C%A8%E5%81%9A%E4%BB%80%E4%B9%88.md
	https://github.com/pudongdong/NLP_ability#1kafka
	https://github.com/pudongdong/NLP_ability#2docker
	https://github.com/pudongdong/NLP_ability#3elasticsearch
	https://github.com/pudongdong/NLP_ability#4flasknginx
	https://github.com/pudongdong/NLP_ability#5-grpc
	https://github.com/pudongdong/NLP_ability#6-tensorrt
Readme	https://github.com/pudongdong/NLP_ability#readme-ov-file
Please reload this page	https://github.com/pudongdong/NLP_ability
Activity	https://github.com/pudongdong/NLP_ability/activity
1 fork	https://github.com/pudongdong/NLP_ability/forks
Report repository	https://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Fpudongdong%2FNLP_ability&report=pudongdong+%28user%29
Releases	https://github.com/pudongdong/NLP_ability/releases
Packages 0	https://github.com/users/pudongdong/packages?repo_name=NLP_ability
Please reload this page	https://github.com/pudongdong/NLP_ability
Contributors	https://github.com/pudongdong/NLP_ability/graphs/contributors
Please reload this page	https://github.com/pudongdong/NLP_ability
	https://github.com
Terms	https://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacy	https://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Security	https://github.com/security
Status	https://www.githubstatus.com/
Community	https://github.community/
Docs	https://docs.github.com/
Contact	https://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.