58 Open Source Chinese Nlp Software Projects

:orange_book: 中华新华字典数据库。包括歇后语，成语，词语，汉字。

A curated list of resources for Chinese NLP 中文自然语言处理相关资料

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

Language Technology Platform

百度NLP：分词，词性标注，命名实体识别

fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

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

An Efficient Lexical Analyzer for Chinese

Datasets, SOTA results of every fields of Chinese NLP

Jcseg is a light weight NLP framework developed with Java. Provide CJK and English segmentation based on MMSEG algorithm, With also keywords extraction, key sentence extraction, summary extraction implemented based on TEXTRANK algorithm. Jcseg had a build-in http server and search modules for the latest lucene,solr,elasticsearch

An Efficient Lexical Analyzer for Chinese

:four_leaf_clover: Another Chinese chatbot implemented in PyTorch, which is the sub-module of intelligent work order processing robot. 👩‍🔧

SpaCy 中文模型 | Models for SpaCy that support Chinese

Some useful Chinese corpus datasets 中文语料小数据

微信公众号语料库

zhparser is a PostgreSQL extension for full-text search of Chinese language

Collections of Chinese NLP corpus

百度开源的依存句法分析系统

Photographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。

An Efficient Lexical Analyzer for Chinese

An Efficient Chinese Text Classifier

一个基于 Rasa 的中文天气情况问询机器人(chatbot), 带 Web UI 界面

g2pC: A Context-aware Grapheme-to-Phoneme Conversion module for Chinese

PTT 八卦版問答中文語料

任何 JS 环境可用的中文分词包，fork from leizongmin/node-segment

Chinese speech recognition

一个微型&算法全面的中文分词引擎 | A micro tokenizer for Chinese

使用 RASA NLU 来构建中文自然语言理解系统（NLU）| Use RASA NLU to build a Chinese Natural Language Understanding System (NLU)

Chinese Open Information Extraction (Tree-based Triple Relation Extraction Module)

THU Chinese Keyphrase Extraction Toolkit

中文聊天机器人，基于10万组对白训练而成，采用注意力机制，对一般问题都会生成一个有意义的答复。已上传模型，可直接运行，跑不起来直播吃键盘。

NLP for human. A fast and easy-to-use natural language processing (NLP) toolkit, satisfying your imagination about NLP.

基于 Bi-LSTM 和 CRF 的中文语义角色标注

A dataset contains 37 million douban dushu comments

Deep natural language process toolkit

named entity recognition for Chinese.

An Efficient Lexical Analyzer for Chinese

DeepDive Tutorial with Chinese Support

Chinese Question Classifier (Keras Implementation) on BQuLD

classic Chinese punctuate experiment with keras using daizhige(殆知阁古代文献藏书) dataset

This package provide the Korean and English, Chinese morphological analyzer on R.

This is a chinese Bert model specific for question answering

This is a java version of Chinese tokenization descried in BERT.

Chinese Tokenizer module for Python

使用词性模板抽取中文语料中的名词短语

Berserker - BERt chineSE woRd toKenizER

Chinese implementation of the Python official interface for Stanford CoreNLP Java server application to parse, tokenize, part-of-speech tag, etc. Chinese texts.

一套针对中文实体识别的BLSTM-CRF解决方案

This is an implementation of electra according to the paper {ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators}

rasa_nlu中文案例

An unsupervised Chinese word segmentation tool.

运用cnn + highway network网络结构中文文本分类

explores Chinese language models with sub-character level visual information

人工智能与数据科学资源中文索引

A curated list of resources dedicated to word segmentation

汉字数据集，包括汉字的相关信息，例如笔画数、部首、拼音、英文释义/同义词等。

中文->英文的机器翻译，完全基于kreas-transformer。模型已上传，可直接跑。

This is a task on Chinese chat title NER via BERT-BiLSTM-CRF model.