欢迎大家赞助一杯啤酒🍺 我们准备了下酒菜:Formal mathematics/Isabelle/ML, Formal verification/Coq/ACL2/Agda, C++/Lisp/Haskell
Natural language processing
来自开放百科 - 灰狐
				
								
				(版本间的差异)
				
																
				
				
								
小 (→图集)  | 
			小 (→链接)  | 
			||
| (未显示1个用户的14个中间版本) | |||
| 第7行: | 第7行: | ||
==项目==  | ==项目==  | ||
| − | + | [[文件:gate-logo.png|right|Gate]]  | |
*[https://github.com/edobashira/speech-language-processing Speech and Natural Language Processing] [[image:awesome.png]]  | *[https://github.com/edobashira/speech-language-processing Speech and Natural Language Processing] [[image:awesome.png]]  | ||
| + | *[https://nlpprogress.com/ NLP-progress] Tracking Progress in Natural Language Processing  | ||
| + | *[https://github.com/huggingface/transformers Transformers] 为 Jax、[[PyTorch]] 和 [[TensorFlow]] 打造的先进的自然语言处理,提供了数以千计的预训练模型,支持 100 多种语言的文本分类、信息抽取、问答、摘要、翻译、文本生成。它的宗旨让最先进的 NLP 技术人人易用。  | ||
| + | *[https://aclweb.org/aclwiki/Tools_and_Software_for_English Software for Computational Linguistics and Natural Language Processing]   | ||
| + | *[https://github.com/RaRe-Technologies/gensim gensim] Topic Modelling for Humans  | ||
*[https://github.com/facebookresearch/fastText fastText]  | *[https://github.com/facebookresearch/fastText fastText]  | ||
*[https://github.com/facebookresearch/DrQA DrQA] Reading Wikipedia to Answer Open-Domain Questions     | *[https://github.com/facebookresearch/DrQA DrQA] Reading Wikipedia to Answer Open-Domain Questions     | ||
| 第17行: | 第21行: | ||
*[[ScalaNLP]]  | *[[ScalaNLP]]  | ||
*[[Natural Language Toolkit]]  | *[[Natural Language Toolkit]]  | ||
| + | *[[Haskell]] [https://wiki.haskell.org/Applications_and_libraries/Linguistics Computational Linguistics(计算语言学)]  | ||
*[http://nlp.stanford.edu/ Stanford NLP Group], [http://nlp.stanford.edu/projects/chinese-nlp.shtml 斯坦福大学自然语言处理工具]  | *[http://nlp.stanford.edu/ Stanford NLP Group], [http://nlp.stanford.edu/projects/chinese-nlp.shtml 斯坦福大学自然语言处理工具]  | ||
*[https://github.com/stanfordnlp Stanford NLP @ GitHub]  | *[https://github.com/stanfordnlp Stanford NLP @ GitHub]  | ||
*[https://github.com/NLPchina NLPChina: 中国自然语言处理开源组织]  | *[https://github.com/NLPchina NLPChina: 中国自然语言处理开源组织]  | ||
| + | *[https://gate.ac.uk/ GATE] a full-lifecycle open source solution for text processing  | ||
| + | *[https://github.com/thunlp THUNLP] Natural Language Processing Lab at Tsinghua University  | ||
| + | *[https://github.com/HIT-SCIR/ltp 哈工大 LTP(Language Technology Platform)]  | ||
| + | *[https://github.com/languagetool-org LanguageTool] 是一款开源(LGPL)多语言语法、风格和拼写检查器  | ||
==NLU & Bot==  | ==NLU & Bot==  | ||
| 第27行: | 第36行: | ||
*[https://github.com/botpress/botpress Botpress] The open-source bot platform, [[TypeScript]]和[[JavaScript]]驱动  | *[https://github.com/botpress/botpress Botpress] The open-source bot platform, [[TypeScript]]和[[JavaScript]]驱动  | ||
*[https://github.com/Urinx/WeixinBot WeixinBot] 网页版微信API,包含终端版微信及微信机器人  | *[https://github.com/Urinx/WeixinBot WeixinBot] 网页版微信API,包含终端版微信及微信机器人  | ||
| + | |||
| + | ==机器翻译==  | ||
| + | [[Machine translation]]  | ||
==开放数据==  | ==开放数据==  | ||
| 第32行: | 第44行: | ||
==文档==  | ==文档==  | ||
| + | *[https://aclweb.org/aclwiki/Best_paper_awards ACL,NAACL,EMNLP,IJCNLP Best paper awards]  | ||
*[http://docs.huihoo.com/deep-learning/Deep-Learning-for-Natural-Language-Processing-CCF-ADL-20160529.pdf Deep Learning for Natural Language Processing]  | *[http://docs.huihoo.com/deep-learning/Deep-Learning-for-Natural-Language-Processing-CCF-ADL-20160529.pdf Deep Learning for Natural Language Processing]  | ||
*[http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/NLP-and-Deep-Learning-1-Human-Language-and-Word-Vectors.pdf NLP and Deep Learning 1: Human Language & Word Vectors]  | *[http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/http://docs.huihoo.com/deep-learning/deeplearningsummerschool/2015/NLP-and-Deep-Learning-1-Human-Language-and-Word-Vectors.pdf NLP and Deep Learning 1: Human Language & Word Vectors]  | ||
| 第50行: | 第63行: | ||
image:nlp-nlu-engineer-skill-tree.png|技能树  | image:nlp-nlu-engineer-skill-tree.png|技能树  | ||
image:AnyQ-Framework.png|AnyQ问答系统框架  | image:AnyQ-Framework.png|AnyQ问答系统框架  | ||
| + | image:gate-apis.png|Gate  | ||
| + | image:ltp-framework.png|LTP  | ||
</gallery>  | </gallery>  | ||
==链接==  | ==链接==  | ||
| + | *[https://www.aclweb.org Association for Computational Linguistics]  | ||
*[https://www.xenonstack.com/blog/overview-of-artificial-intelligence-and-role-of-natural-language-processing-in-big-data Overview of Artificial Intelligence and Role of Natural Language Processing in Big Data]  | *[https://www.xenonstack.com/blog/overview-of-artificial-intelligence-and-role-of-natural-language-processing-in-big-data Overview of Artificial Intelligence and Role of Natural Language Processing in Big Data]  | ||
*[http://www.infoq.com/cn/articles/predicting-movie-ratings-nlp 预测电影评级:NLP正是电影公司所需要的]  | *[http://www.infoq.com/cn/articles/predicting-movie-ratings-nlp 预测电影评级:NLP正是电影公司所需要的]  | ||
| 第66行: | 第82行: | ||
*[https://www.jiqizhixin.com/articles/2018-12-19-17 一文详解维基百科的开放性问答系统]  | *[https://www.jiqizhixin.com/articles/2018-12-19-17 一文详解维基百科的开放性问答系统]  | ||
| + | [[category:computational linguistics]]  | ||
[[category:natural language processing]]  | [[category:natural language processing]]  | ||
[[category:speech recognition]]  | [[category:speech recognition]]  | ||
| − | [[category:  | + | [[category:artificial intelligence]]  | 
| + | [[category:computer science]]  | ||
2022年8月9日 (二) 10:11的最后版本
|   | 
您可以在Wikipedia上了解到此条目的英文信息 Natural language processing Thanks, Wikipedia. | 
Natural language processing(简称NLP) 自然语言处理是人工智能和语言学领域的分支学科。
目录 | 
[编辑] 简介
Deep Learning is becoming hot in Natural Language Processing
[编辑] 项目
- Speech and Natural Language Processing 
 - NLP-progress Tracking Progress in Natural Language Processing
 - Transformers 为 Jax、PyTorch 和 TensorFlow 打造的先进的自然语言处理,提供了数以千计的预训练模型,支持 100 多种语言的文本分类、信息抽取、问答、摘要、翻译、文本生成。它的宗旨让最先进的 NLP 技术人人易用。
 - Software for Computational Linguistics and Natural Language Processing
 - gensim Topic Modelling for Humans
 - fastText
 - DrQA Reading Wikipedia to Answer Open-Domain Questions
 - Apache UIMA
 - DeepDive
 - DeepPavlov
 - Apache OpenNLP
 - ScalaNLP
 - Natural Language Toolkit
 - Haskell Computational Linguistics(计算语言学)
 - Stanford NLP Group, 斯坦福大学自然语言处理工具
 - Stanford NLP @ GitHub
 - NLPChina: 中国自然语言处理开源组织
 - GATE a full-lifecycle open source solution for text processing
 - THUNLP Natural Language Processing Lab at Tsinghua University
 - 哈工大 LTP(Language Technology Platform)
 - LanguageTool 是一款开源(LGPL)多语言语法、风格和拼写检查器
 
[编辑] NLU & Bot
- BotSharp Conversation as a platform (CaaP) is the future.
 - Microsoft Bot Builder
 - ChatterBot Python驱动
 - Botpress The open-source bot platform, TypeScript和JavaScript驱动
 - WeixinBot 网页版微信API,包含终端版微信及微信机器人
 
[编辑] 机器翻译
[编辑] 开放数据
[编辑] 文档
- ACL,NAACL,EMNLP,IJCNLP Best paper awards
 - Deep Learning for Natural Language Processing
 - NLP and Deep Learning 1: Human Language & Word Vectors
 - NLP and Deep Learning 2: Compositonal Deep Learning
 - Deep NLP Recurrent Neural Networks
 - Memory, Reading, and Comprehension
 - Deep NLP Applications and Dynamic Memory Networks
 
[编辑] 图书
[编辑] 图集
[编辑] 链接
- Association for Computational Linguistics
 - Overview of Artificial Intelligence and Role of Natural Language Processing in Big Data
 - 预测电影评级:NLP正是电影公司所需要的
 - 斯坦福大学深度学习与自然语言处理第一讲:引言
 - 斯坦福大学深度学习与自然语言处理第二讲:词向量
 - 斯坦福大学深度学习与自然语言处理第三讲:高级的词向量表示
 - 用MeCab打造一套实用的中文分词系统(一)
 - 用MeCab打造一套实用的中文分词系统(二)
 - 用MeCab打造一套实用的中文分词系统(三):MeCab-Chinese
 - 用MeCab打造一套实用的中文分词系统(四):MeCab增量更新
 - 无限大地NLP_空木的专栏,研究自然语言处理、机器学习、信息抽取等方向
 - 清华大学自然语言处理与社会人文计算实验室
 - 一文详解维基百科的开放性问答系统
 
	分享您的观点
			
			
			
			
			
				
								
				
								
			