{"id":13348409,"url":"https://github.com/crownpku/Awesome-Chinese-NLP","last_synced_at":"2025-03-12T08:31:28.570Z","repository":{"id":39351884,"uuid":"97191792","full_name":"crownpku/Awesome-Chinese-NLP","owner":"crownpku","description":"A curated list of resources for Chinese NLP 中文自然语言处理相关资料","archived":false,"fork":false,"pushed_at":"2023-07-27T02:54:52.000Z","size":325,"stargazers_count":7692,"open_issues_count":3,"forks_count":1706,"subscribers_count":389,"default_branch":"master","last_synced_at":"2024-05-20T00:00:47.531Z","etag":null,"topics":["chinese-nlp","nlp"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/crownpku.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"contributing.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null},"funding":{"github":"crownpku","patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"custom":null}},"created_at":"2017-07-14T04:07:08.000Z","updated_at":"2024-05-19T07:08:30.000Z","dependencies_parsed_at":"2024-01-07T00:07:37.497Z","dependency_job_id":"78fd8b7b-910f-4855-8089-5c8ea93ea767","html_url":"https://github.com/crownpku/Awesome-Chinese-NLP","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FAwesome-Chinese-NLP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FAwesome-Chinese-NLP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FAwesome-Chinese-NLP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FAwesome-Chinese-NLP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/crownpku","download_url":"https://codeload.github.com/crownpku/Awesome-Chinese-NLP/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221279990,"owners_count":16790563,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chinese-nlp","nlp"],"created_at":"2024-07-29T20:01:53.962Z","updated_at":"2024-10-24T05:31:04.812Z","avatar_url":"https://github.com/crownpku.png","language":null,"funding_links":["https://github.com/sponsors/crownpku"],"categories":["Uncategorized","Others","NLP","Table of Contents","其他_NLP自然语言处理","Others (1002)"],"sub_categories":["Uncategorized","其他_文本生成、文本对话"],"readme":"# awesome-chinese-nlp\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\nA curated list of resources for NLP (Natural Language Processing) for Chinese\n\n中文自然语言处理相关资料\n\n图片来自复旦大学邱锡鹏教授\n\n![](/images/1.jpg)\n  \n  \n## Contents 列表\n\n### 1. [Chinese NLP Toolkits 中文NLP工具](https://github.com/crownpku/awesome-chinese-nlp#chinese-nlp-toolkits-中文nlp工具)\n\n* #### [Toolkits 综合NLP工具包](https://github.com/crownpku/awesome-chinese-nlp#toolkits-综合nlp工具包-1)\n* #### [Popular NLP Toolkits for English/Multi-Language 常用的英文或支持多语言的NLP工具包](https://github.com/crownpku/awesome-chinese-nlp#popular-nlp-toolkits-for-englishmulti-language-常用的英文或支持多语言的nlp工具包-1)\n* #### [Chinese Word Segment 中文分词](https://github.com/crownpku/awesome-chinese-nlp#chinese-word-segment-中文分词-1)\n* #### [Information Extraction 信息提取](https://github.com/crownpku/awesome-chinese-nlp#information-extraction-信息提取-1)\n* #### [QA \u0026 Chatbot 问答和聊天机器人](https://github.com/crownpku/awesome-chinese-nlp#qa--chatbot-问答和聊天机器人-1)\n* #### [Multi-Modal Representation \u0026 Retrieval 多模态表征与检索](https://github.com/crownpku/awesome-chinese-nlp#multi-modal-representation--retrieval-多模态表征与检索-1)\n### 2. [Corpus 中文语料](https://github.com/crownpku/awesome-chinese-nlp#corpus-中文语料)\n### 3. [Organizations 中文NLP学术组织及竞赛](https://github.com/crownpku/awesome-chinese-nlp#organizations-%E4%B8%AD%E6%96%87nlp%E5%AD%A6%E6%9C%AF%E7%BB%84%E7%BB%87%E5%8F%8A%E7%AB%9E%E8%B5%9B)\n### 4. [Industry 中文NLP商业服务](https://github.com/crownpku/awesome-chinese-nlp#industry-%E4%B8%AD%E6%96%87nlp%E5%95%86%E4%B8%9A%E6%9C%8D%E5%8A%A1)\n### 5. [Learning Materials 学习资料](https://github.com/crownpku/awesome-chinese-nlp#learning-materials-学习资料)\n  \n\u003cbr /\u003e\n\u003cbr /\u003e\n\n## Chinese NLP Toolkits 中文NLP工具\n\n### Toolkits 综合NLP工具包\n\n- [THULAC 中文词法分析工具包](http://thulac.thunlp.org/) by 清华 (C++/Java/Python)\n\n- [NLPIR](https://github.com/NLPIR-team/NLPIR) by 中科院 (Java)\n\n- [LTP 语言技术平台](https://github.com/HIT-SCIR/ltp) by 哈工大 (C++)  [pylyp](https://github.com/HIT-SCIR/pyltp) LTP的python封装\n\n- [FudanNLP](https://github.com/FudanNLP/fnlp) by 复旦 (Java)\n\n- [BaiduLac](https://github.com/baidu/lac) by 百度 Baidu's open-source lexical analysis tool for Chinese, including word segmentation, part-of-speech tagging \u0026 named entity recognition. \n\n- [HanLP](https://github.com/hankcs/HanLP) (Java)\n\n- [FastNLP](https://github.com/fastnlp/fastNLP) (Python) 一款轻量级的 NLP 处理套件。\n\n- [SnowNLP](https://github.com/isnowfy/snownlp) (Python) Python library for processing Chinese text\n\n- [YaYaNLP](https://github.com/Tony-Wang/YaYaNLP) (Python) 纯python编写的中文自然语言处理包，取名于“牙牙学语”\n\n- [小明NLP](https://github.com/SeanLee97/xmnlp) (Python) 轻量级中文自然语言处理工具\n\n- [DeepNLP](https://github.com/rockingdingo/deepnlp) (Python) Deep Learning NLP Pipeline implemented on Tensorflow with pretrained Chinese models.\n\n- [chinese_nlp](https://github.com/taozhijiang/chinese_nlp) (C++ \u0026 Python) Chinese Natural Language Processing tools and examples\n\n- [lightNLP](https://github.com/smilelight/lightNLP) (Python) 基于Pytorch和torchtext的自然语言处理深度学习框架\n\n- [Chinese-Annotator](https://github.com/crownpku/Chinese-Annotator) (Python) Annotator for Chinese Text Corpus 中文文本标注工具\n\n- [Poplar](https://github.com/synyi/poplar) (Typescript) A web-based annotation tool for natural language processing (NLP)\n\n- [Jiagu](https://github.com/ownthink/Jiagu) (Python) Jiagu以BiLSTM等模型为基础，使用大规模语料训练而成。将提供中文分词、词性标注、命名实体识别、情感分析、知识图谱关系抽取、关键词抽取、文本摘要、新词发现等常用自然语言处理功能。\n\n- [SmoothNLP](https://github.com/smoothnlp/SmoothNLP) (Python \u0026 Java) 专注于可解释的NLP技术\n\n- [FoolNLTK](https://github.com/rockyzhengwu/FoolNLTK) (Python \u0026 Java) A Chinese Nature Language Toolkit\n\n### Popular NLP Toolkits for English/Multi-Language 常用的英文或支持多语言的NLP工具包\n\n- [CoreNLP](https://github.com/stanfordnlp/CoreNLP) by Stanford (Java) A Java suite of core NLP tools.\n\n- [Stanza](https://github.com/stanfordnlp/stanza) by Stanford (Python) A Python NLP Library for Many Human Languages\n\n- [NLTK](http://www.nltk.org/) (Python) Natural Language Toolkit\n\n- [spaCy](https://spacy.io/) (Python) Industrial-Strength Natural Language Processing with a [online course](https://course.spacy.io/)\n\n- [textacy](https://github.com/chartbeat-labs/textacy) (Python) NLP, before and after spaCy\n\n- [OpenNLP](https://opennlp.apache.org/) (Java) A machine learning based toolkit for the processing of natural language text.\n\n- [gensim](https://github.com/RaRe-Technologies/gensim) (Python) Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. \n\n- [Kashgari](https://github.com/BrikerMan/Kashgari) - Simple and powerful NLP framework, build your state-of-art model in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includes BERT and word2vec embedding.\n\n  \n### Chinese Word Segment 中文分词\n\n- [Jieba 结巴中文分词](https://github.com/fxsjy/jieba) (Python及大量其它编程语言衍生) 做最好的 Python 中文分词组件\n\n- [北大中文分词工具](https://github.com/lancopku/pkuseg-python) (Python) 高准确度中文分词工具，简单易用，跟现有开源工具相比大幅提高了分词的准确率。\n\n- [kcws 深度学习中文分词](https://github.com/koth/kcws) (Python) BiLSTM+CRF与IDCNN+CRF\n\n- [ID-CNN-CWS](https://github.com/hankcs/ID-CNN-CWS) (Python) Iterated Dilated Convolutions for Chinese Word Segmentation\n\n- [Genius 中文分词](https://github.com/duanhongyi/genius) (Python) Genius是一个开源的python中文分词组件，采用 CRF(Conditional Random Field)条件随机场算法。\n\n- [loso 中文分词](https://github.com/fangpenlin/loso) (Python)\n\n- [yaha \"哑哈\"中文分词](https://github.com/jannson/yaha) (Python)\n\n- [ChineseWordSegmentation](https://github.com/Moonshile/ChineseWordSegmentation) (Python) Chinese word segmentation algorithm without corpus（无需语料库的中文分词）\n\n- [Go语言高性能分词](https://github.com/go-ego/gse) (Go) Go efficient text segmentation; support english, chinese, japanese and other.\n\n- [Ansj中文分词](https://github.com/NLPchina/ansj_seg) (java) 基于n-Gram+CRF+HMM的中文分词的java实现 \n\n  \n### Information Extraction 信息提取\n\n- [MITIE](https://github.com/mit-nlp/MITIE) (C++) library and tools for information extraction\n\n- [Duckling](https://github.com/facebookincubator/duckling) (Haskell) Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.\n\n- [IEPY](https://github.com/machinalis/iepy) (Python)  IEPY is an open source tool for Information Extraction focused on Relation Extraction.\n\n- [Snorkel](https://github.com/HazyResearch/snorkel) A training data creation and management system focused on information extraction \n\n- [Neural Relation Extraction implemented with LSTM in TensorFlow](https://github.com/thunlp/TensorFlow-NRE)\n\n- [A neural network model for Chinese named entity recognition](https://github.com/zjy-ucas/ChineseNER)\n\n- [bert-chinese-ner](https://github.com/ProHiryu/bert-chinese-ner) 使用预训练语言模型BERT做中文NER\n\n- [Information-Extraction-Chinese](https://github.com/crownpku/Information-Extraction-Chinese) Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取\n\n- [Familia](https://github.com/baidu/Familia) 百度出品的 A Toolkit for Industrial Topic Modeling\n\n- [Text Classification](https://github.com/brightmart/text_classification) All kinds of text classificaiton models and more with deep learning. 用知乎问答语聊作为测试数据。\n\n- [ComplexEventExtraction](https://github.com/liuhuanyong/ComplexEventExtraction) 中文复合事件的概念与显式模式，包括条件事件、因果事件、顺承事件、反转事件等事件抽取，并形成事理图谱。\n\n- [TextRank4ZH](https://github.com/letiantian/TextRank4ZH) 从中文文本中自动提取关键词和摘要\n\n  \n### QA \u0026 Chatbot 问答和聊天机器人 \n\n- [Rasa NLU](https://github.com/RasaHQ/rasa_nlu) (Python) turn natural language into structured data, a Chinese fork at [Rasa NLU Chi](https://github.com/crownpku/Rasa_NLU_Chi)\n\n- [Rasa Core](https://github.com/RasaHQ/rasa_core) (Python) machine learning based dialogue engine for conversational software\n\n- [Chatstack](https://github.com/crownpku/Chatstack-Doc) A Full Pipeline UI for building Chinese NLU System\n\n- [Snips NLU](https://github.com/snipsco/snips-nlu) (Python) Snips NLU is a Python library that allows to parse sentences written in natural language and extracts structured information.\n\n- [DeepPavlov](https://github.com/deepmipt/DeepPavlov) (Python) An open source library for building end-to-end dialog systems and training chatbots.\n\n- [ChatScript](https://github.com/bwilcox-1234/ChatScript) Natural Language tool/dialog manager, a rule-based chatbot engine.\n\n- [Chatterbot](https://github.com/gunthercox/ChatterBot) (Python) ChatterBot is a machine learning, conversational dialog engine for creating chat bots.\n\n- [Chatbot](https://github.com/zake7749/Chatbot) (Python) 基於向量匹配的情境式聊天機器人\n\n- [Tipask](https://github.com/sdfsky/tipask) (PHP) 一款开放源码的PHP问答系统，基于Laravel框架开发，容易扩展，具有强大的负载能力和稳定性。\n\n- [QuestionAnsweringSystem](https://github.com/ysc/QuestionAnsweringSystem) (Java) 一个Java实现的人机问答系统，能够自动分析问题并给出候选答案。\n\n- [QA-Snake](https://github.com/SnakeHacker/QA-Snake) (Python) 基于多搜索引擎和深度学习技术的自动问答\n\n- [使用TensorFlow实现的Sequence to Sequence的聊天机器人模型](https://github.com/qhduan/Seq2Seq_Chatbot_QA) (Python)\n\n- [使用深度学习算法实现的中文阅读理解问答系统](https://github.com/S-H-Y-GitHub/QA) (Python)\n\n- [AnyQ by Baidu](https://github.com/baidu/AnyQ) 主要包含面向FAQ集合的问答系统框架、文本语义匹配工具SimNet。\n\n- [DuReader中文阅读理解Baseline代码](https://github.com/baidu/DuReader) (Python)\n\n- [基于SmartQQ的自动机器人框架](https://github.com/Yinzo/SmartQQBot) (Python)\n\n- [QASystemOnMedicalKG](https://github.com/liuhuanyong/QASystemOnMedicalKG) (Python) 以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。\n\n- [GPT2-chitchat](https://github.com/yangjianxin1/GPT2-chitchat) (Python) 用于中文闲聊的GPT2模型\n\n- [CDial-GPT](https://github.com/thu-coai/CDial-GPT) (Python) 提供了一个大规模中文对话数据集，并提供了在此数据集上的中文对话预训练模型（中文GPT模型）\n\n### Multi-Modal Representation \u0026 Retrieval 多模态表征与检索\n\n- [Chinese-CLIP](https://github.com/OFA-Sys/Chinese-CLIP) (Python) Chinese-CLIP是中文多模态图文表征预训练模型。其基于OpenAI的CLIP模型结构，利用大规模中文原生图文语料完成预训练，目前开源了多个模型规模，同时公开了技术报告论文及检索demo\n\n\u003cbr /\u003e\n\u003cbr /\u003e\n\n## Corpus 中文语料\n\n- [开放知识图谱OpenKG.cn](http://openkg.cn)\n\n- [开放中文知识图谱的schema](https://github.com/cnschema/cnschema)\n\n- [大规模中文概念图谱CN-Probase](http://kw.fudan.edu.cn/cnprobase/search/) [公众号介绍](https://mp.weixin.qq.com/s?__biz=MzI0MTI1Nzk1MA==\u0026mid=2651675884\u0026idx=1\u0026sn=1a43a93fd5bb53c8a9e48518bfa41db8\u0026chksm=f2f7a05dc580294b227332b1051bfa2e5c756c72efb4d102c83613185b571ac31343720a6eae\u0026mpshare=1\u0026scene=1\u0026srcid=1113llNDS1MvoadhCki83ERW#rd)\n\n- [大规模1.4亿中文知识图谱开源下载](https://github.com/ownthink/KnowledgeGraphData)\n\n- [农业知识图谱](https://github.com/qq547276542/Agriculture_KnowledgeGraph) 农业领域的信息检索，命名实体识别，关系抽取，分类树构建，数据挖掘\n\n- [CLDC中文语言资源联盟](http://www.chineseldc.org/)\n\n- [中文 Wikipedia Dump](https://dumps.wikimedia.org/zhwiki/)\n\n- [基于不同语料、不同模型（比如BERT、GPT）的中文预训练模型](https://github.com/dbiir/UER-py) 中文预训练模型框架，支持不同语料、编码器、目标任务的预训练模型（from RUC and Tencent）\n\n- [OpenCLaP](https://github.com/thunlp/OpenCLaP) 多领域开源中文预训练语言模型仓库 (from Tsinghua)\n\n- [98年人民日报词性标注库@百度盘](https://pan.baidu.com/s/1gd6mslt)\n\n- [搜狗20061127新闻语料(包含分类)@百度盘](https://pan.baidu.com/s/1bnhXX6Z)\n\n- [UDChinese](https://github.com/UniversalDependencies/UD_Chinese) (for training spaCy POS)\n\n- [中文word2vec模型](https://github.com/to-shimo/chinese-word2vec)\n\n- [上百种预训练中文词向量](https://github.com/Embedding/Chinese-Word-Vectors)\n\n- [Tencent AI Lab Embedding Corpus for Chinese Words and Phrases](https://ai.tencent.com/ailab/nlp/embedding.html)\n\n- [中文预训练BERT with Whole Word Masking](https://github.com/ymcui/Chinese-BERT-wwm)\n\n- [中文GPT2训练代码](https://github.com/Morizeyao/GPT2-Chinese) 可以写诗，新闻，小说，或是训练通用语言模型。\n\n- [中文语言理解测评基准ChineseGLUE](https://github.com/chineseGLUE/chineseGLUE) 包括代表性的数据集、基准(预训练)模型、语料库、排行榜。\n\n- [中华新华字典数据库](https://github.com/pwxcoo/chinese-xinhua) 包括歇后语，成语，词语，汉字。\n\n- [Synonyms:中文近义词工具包](https://github.com/huyingxi/Synonyms/) 基于维基百科中文和word2vec训练的近义词库，封装为python包文件。\n\n- [Chinese_conversation_sentiment](https://github.com/z17176/Chinese_conversation_sentiment) A Chinese sentiment dataset may be useful for sentiment analysis.\n\n- [中文突发事件语料库](https://github.com/shijiebei2009/CEC-Corpus) Chinese Emergency Corpus\n\n- [dgk_lost_conv 中文对白语料](https://github.com/rustch3n/dgk_lost_conv) chinese conversation corpus\n\n- [用于训练中英文对话系统的语料库](https://github.com/candlewill/Dialog_Corpus) Datasets for Training Chatbot System \n\n- [八卦版問答中文語料](https://github.com/zake7749/Gossiping-Chinese-Corpus)\n\n- [中文公开聊天语料库](https://github.com/codemayq/chaotbot_corpus_Chinese)\n\n- [中国股市公告信息爬取](https://github.com/startprogress/China_stock_announcement) 通过python脚本从巨潮网络的服务器获取中国股市（sz,sh）的公告(上市公司和监管机构)\n\n- [tushare财经数据接口](http://tushare.org/) TuShare是一个免费、开源的python财经数据接口包。\n\n- [金融文本数据集](https://github.com/smoothnlp/FinancialDatasets) SmoothNLP 金融文本数据集(公开) Public Financial Datasets for NLP Researches\n\n- [保险行业语料库](https://github.com/Samurais/insuranceqa-corpus-zh)   [[52nlp介绍Blog](http://www.52nlp.cn/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E4%BF%9D%E9%99%A9%E8%A1%8C%E4%B8%9A%E9%97%AE%E7%AD%94%E5%BC%80%E6%94%BE%E6%95%B0%E6%8D%AE%E9%9B%86)] OpenData in insurance area for Machine Learning Tasks\n\n- [最全中华古诗词数据库](https://github.com/chinese-poetry/chinese-poetry) 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。\n\n- [DuReader中文阅读理解数据](http://ai.baidu.com/broad/subordinate?dataset=dureader) \n\n- [中文语料小数据](https://github.com/crownpku/Small-Chinese-Corpus) 包含了中文命名实体识别、中文关系识别、中文阅读理解等一些小量数据\n\n- [Chinese-Literature-NER-RE-Dataset](https://github.com/lancopku/Chinese-Literature-NER-RE-Dataset) A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text\n\n- [ChineseTextualInference](https://github.com/liuhuanyong/ChineseTextualInference) 中文文本推断项目,包括88万文本蕴含中文文本蕴含数据集的翻译与构建,基于深度学习的文本蕴含判定模型构建.\n\n- [大规模中文自然语言处理语料](https://github.com/brightmart/nlp_chinese_corpus) 维基百科(wiki2019zh),新闻语料(news2016zh),百科问答(baike2018qa)\n\n- [中文人名语料库](https://github.com/wainshine/Chinese-Names-Corpus) 中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。\n\n- [公司名、机构名语料库](https://github.com/wainshine/Company-Names-Corpus) 公司简称,缩写,品牌词,企业名。\n\n- [中文敏感词词库](https://github.com/observerss/textfilter) 敏感词过滤的几种实现+某1w词敏感词库\n\n- [中文简称词库](https://github.com/zhangyics/Chinese-abbreviation-dataset) A corpus of Chinese abbreviation, including negative full forms.   \n\n- [中文数据预处理材料](https://github.com/dongxiexidian/Chinese) 中文分词词典和中文停用词\n\n- [漢語拆字字典](https://github.com/kfcd/chaizi)\n\n- [SentiBridge: 中文实体情感知识库](https://github.com/rainarch/SentiBridge) 刻画人们如何描述某个实体，包含新闻、旅游、餐饮，共计30万对。\n\n- [OpenCorpus](https://github.com/hankcs/OpenCorpus) A collection of freely available (Chinese) corpora. \n\n- [ChineseNlpCorpus](https://github.com/SophonPlus/ChineseNlpCorpus) 情感/观点/评论 倾向性分析，中文命名实体识别，推荐系统\n\n- [FinancialDatasets](https://github.com/smoothnlp/FinancialDatasets) SmoothNLP 金融文本数据集(公开) Public Financial Datasets for NLP Researches Only\n\n- [People's Daily \u0026 Children's Fairy Tale](https://github.com/ymcui/Chinese-Cloze-RC) PD\u0026CFT: A Chinese Reading Comprehension Dataset\n- [中文维基23万高质量词条-更新至23年7月-已过滤敏感或争议性信息](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)\n\u003cbr /\u003e\n\u003cbr /\u003e\n\n## Organizations 中文NLP学术组织及竞赛\n\n- [清华大学自然语言处理与人文计算实验室](http://nlp.csai.tsinghua.edu.cn/site2/index.php/zh)\n\n- [北京大学计算语言学教育部重点实验室](http://klcl.pku.edu.cn/)\n\n- [中科院计算所自然语言处理研究组](http://www.nlpir.org/)\n\n- [哈工大智能技术与自然语言处理实验室](http://insun.hit.edu.cn/)\n\n- [哈工大社会计算与信息检索研究中心](http://ir.hit.edu.cn/)\n\n- [复旦大学自然语言处理组](http://nlp.fudan.edu.cn/)\n\n- [苏州大学自然语言处理组](http://nlp.suda.edu.cn/index.html)\n\n- [南京大学自然语言处理研究组](http://nlp.nju.edu.cn)\n\n- [东北大学自然语言处理实验室](http://www.nlplab.com/)\n\n- [厦门大学智能科学与技术系自然语言处理实验室](http://nlp.xmu.edu.cn/)\n\n- [郑州大学自然语言处理实验室](http://nlp.zzu.edu.cn/)\n\n- [微软亚洲研究院自然语言处理](https://www.msra.cn/zh-cn/research/nlp)\n\n- [华为诺亚方舟实验室](http://www.noahlab.com.hk/)\n\n- [CUHK Text Mining Group](http://www1.se.cuhk.edu.hk/~textmine/)\n\n- [PolyU Social Media Mining Group](http://www4.comp.polyu.edu.hk/~cswjli/Group.html)\n\n- [HKUST Human Language Technology Center](http://www.cse.ust.hk/~hltc/)\n\n- [National Taiwan University NLP Lab](http://nlg.csie.ntu.edu.tw/)\n\n- [中国中文信息学会](http://www.cipsc.org.cn/)\n\n- [NLP Conference Calender](http://cs.rochester.edu/~omidb/nlpcalendar/) Main conferences, journals, workshops and shared tasks in NLP community.\n\n- [2017 第一届“讯飞杯”中文机器阅读理解评测](http://www.cips-cl.org/static/CCL2017/iflytek.html)\n\n- [2017 AI-Challenger 图像中文描述](https://www.challenger.ai/competition/caption) 用一句话描述给定图像中的主要信息，挑战中文语境下的图像理解问题。\n\n- [2017 AI-Challenger 英中机器文本翻译](https://www.challenger.ai/competition/translation) 用大规模的数据，提升英中文本机器翻译模型的能力。\n\n- [2017 知乎看山杯机器学习挑战赛](https://biendata.com/competition/zhihu/) 根据知乎给出的问题及话题标签的绑定关系的训练数据，训练出对未标注数据自动标注的模型。\n\n- [2018 开放领域的中文问答任务](https://biendata.com/competition/CCKS2018_4/) 对于给定的一句中文问题，问答系统从给定知识库中选择若干实体或属性值作为该问题的答案。\n\n- [2018 微众银行智能客服问句匹配大赛](https://biendata.com/competition/CCKS2018_3/) 针对中文的真实客服语料，进行问句意图匹配；给定两个语句，判定两者意图是否相近。\n  \n\u003cbr /\u003e\n\u003cbr /\u003e\n\n## Industry 中文NLP商业服务\n\n- [华为云NLP](https://www.huaweicloud.com/product/nlp.html) 针对各类企业及开发者提供的用于文本分析及挖掘的云服务，旨在帮助用户高效的处理文本\n\n- [百度云NLP](https://cloud.baidu.com/product/nlp.html) 提供业界领先的自然语言处理技术，提供优质文本处理及理解技术\n\n- [阿里云NLP](https://data.aliyun.com/product/nlp) 为各类企业及开发者提供的用于文本分析及挖掘的核心工具\n\n- [腾讯云NLP](https://cloud.tencent.com/product/nlp) 基于并行计算、分布式爬虫系统，结合独特的语义分析技术，一站满足NLP、转码、抽取、数据抓取等需求\n\n- [讯飞开放平台](https://www.xfyun.cn/) 以语音交互为核心的人工智能开放平台\n\n- [搜狗实验室](http://www.sogou.com/labs/webservice/) 分词和词性标注\n\n- [玻森数据](http://bosonnlp.com/) 上海玻森数据科技有限公司，专注中文语义分析技术\n\n- [云孚科技](https://www.yunfutech.com/) NLP工具包、知识图谱、文本挖掘、对话系统、舆情分析等\n\n- [智言科技](http://www.webot.ai) 专注于深度学习和知识图谱技术突破的人工智能公司\n\n- [追一科技](https://zhuiyi.ai/) 主攻深度学习和自然语言处理\n\n\u003cbr /\u003e\n\u003cbr /\u003e\n\n## Learning Materials 学习资料\n\n- [中文Deep Learning Book](https://github.com/exacity/deeplearningbook-chinese)\n\n- [Stanford CS224n Natural Language Processing with Deep Learning 2017](http://web.stanford.edu/class/cs224n/syllabus.html)\n\n- [Oxford CS DeepNLP 2017](https://github.com/oxford-cs-deepnlp-2017)\n\n- [Course materials for Georgia Tech CS 4650 and 7650, \"Natural Language\"] (https://github.com/jacobeisenstein/gt-nlp-class)\n\n- [Speech and Language Processing](https://web.stanford.edu/~jurafsky/slp3/) by Dan Jurafsky and James H. Martin\n\n- [52nlp 我爱自然语言处理](http://www.52nlp.cn/)\n\n- [hankcs 码农场](http://www.hankcs.com/)\n\n- [文本处理实践课资料](https://github.com/Roshanson/TextInfoExp) 文本处理实践课资料，包含文本特征提取（TF-IDF），文本分类，文本聚类，word2vec训练词向量及同义词词林中文词语相似度计算、文档自动摘要，信息抽取，情感分析与观点挖掘等实验。\n\n- [nlp_tasks](https://github.com/Kyubyong/nlp_tasks) Natural Language Processing Tasks and Selected References\n\n- [NLP研究入门之道](https://github.com/zibuyu/research_tao) from清华刘知远老师\n\n- [Chinese NLP](https://chinesenlp.xyz/#/) Shared tasks, datasets and state-of-the-art results for Chinese Natural Language Processing \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrownpku%2FAwesome-Chinese-NLP","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcrownpku%2FAwesome-Chinese-NLP","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrownpku%2FAwesome-Chinese-NLP/lists"}