yangqiokay / awesome-chinese-nlp

A curated list of resources for NLP (Natural Language Processing) for Chinese 中文自然语言处理相关资料

awesome-chinese-nlp

A curated list of resources for NLP (Natural Language Processing) for Chinese 中文自然语言处理相关资料

Chinese NLP Toolkits 中文NLP工具

Toolkits 综合NLP工具包

• THULAC 中文词法分析工具包 by 清华 (C++/Java/Python) [link]

• NLPIR by 中科院 (Java) [github]

• LTP 语言技术平台 by 哈工大 (C++) [github]

• FudanNLP by 复旦 (Java) [github]

• CoreNLP by Stanford (Java) [github]

• BosonNLP by Boson (商业API服务) [link]

• HanNLP (Java) [github]

• SnowNLP (Python) [github] Python library for processing Chinese text

• YaYaNLP (Python) [github] 纯python编写的中文自然语言处理包，取名于“牙牙学语”

• DeepNLP (Python) [github] Deep Learning NLP Pipeline implemented on Tensorflow with pretrained Chinese models.

• chinese_nlp (C++ & Python) [github] Chinese Natural Language Processing tools and examples

Popular NLP Toolkits for English/Multi-Language 常用的英文或支持多语言的NLP工具包

• CoreNLP by Stanford (Java) [github]

• NLTK (Python) [link]

• spaCy (Python) [link]

• OpenNLP (Java) [link]

• gensim (Python) [github] Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora.

Chinese Word Segment 中文分词

• Jieba 结巴中文分词 (Python) [github] 做最好的 Python 中文分词组件

• kcws 深度学习中文分词 (Python) [github] BiLSTM+CRF与IDCNN+CRF

• Genius 中文分词 (Python) [github] 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。

• loso 中文分词 (Python) [github]

Information Extraction 信息提取

• MITIE (C++) [github] library and tools for information extraction

• Duckling (Haskell) [github] Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.

• IEPY (Python) [github] IEPY is an open source tool for Information Extraction focused on Relation Extraction.

• Snorkel: A training data creation and management system focused on information extraction [github]

• Neural Relation Extraction implemented with LSTM in TensorFlow [github]

• A neural network model for Chinese named entity recognition [github]

Natrual Language Understanding 自然语言理解

• Rasa NLU (Python) [github] turn natural language into structured data

QA & Chatbot 问答和聊天机器人

• Chatterbot (Python) [github] ChatterBot is a machine learning, conversational dialog engine for creating chat bots.

• Chatbot (Python) [github] 基於向量匹配的情境式聊天機器人

• Tipask (PHP) [github] 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。

• QuestionAnsweringSystem (Java) [github] 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。

• 使用TensorFlow实现的Sequence to Sequence的聊天机器人模型 (Python) [github]

Corpus 中文语料

• 开放知识图谱OpenKG.cn [link]

• CLDC中文语言资源联盟 [link]

• 用于训练中英文对话系统的语料库 Datasets for Training Chatbot System [github]

• 中文 Wikipedia Dump [link]

• 98年人民日报词性标注库@百度盘 [link]

• 百度百科100gb语料@百度盘) [link] 密码neqs 出处应该是梁斌penny大神

• 搜狗20061127新闻语料(包含分类)@百度盘 [link]

• UDChinese (for training spaCy POS) [github]

• 八卦版問答中文語料 [github]

• 中文word2vec模型 [github]

• 中文突发事件语料库（Chinese Emergency Corpus）[github]

• dgk_lost_conv 中文对白语料 chinese conversation corpus [github]

• 漢語拆字字典 [github]

• **股市公告信息爬取 [github] 通过python脚本从巨潮网络的服务器获取**股市（sz,sh）的公告(上市公司和监管机构)

• tushare财经数据接口 [website] TuShare是一个免费、开源的python财经数据接口包。

• 保险行业语料库 [github] [52nlp介绍Blog] OpenData in insurance area for Machine Learning Tasks

• 最全中华古诗词数据库 [github] 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。

Organizations 相关中文NLP组织和会议

• **中文信息学会 [website]

• NLP Conference Calender [website] Main conferences, journals, workshops and shared tasks in NLP community.

Learning Materials 学习资料

• 中文Deep Learning Book [github]

• Stanford CS224n Natural Language Processing with Deep Learning 2017 [link]

• Oxford CS DeepNLP 2017 [github]

• Speech and Language Processing by Dan Jurafsky and James H. Martin [link]

• 52nlp 我爱自然语言处理 [blog]

• hankcs 码农场 [blog]

• 文本处理实践课资料 [github] 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。