Chinese NLP Toolkits NLP Tools

Comprehensive NLP toolkits and frameworks specifically designed for Chinese language processing, including segmentation, POS tagging, NER, sentiment analysis, and classical Chinese support. Does NOT include language-agnostic NLP tools, machine translation systems, or tools focused on non-Chinese languages.

There are 73 chinese nlp toolkits tools tracked. 3 score above 70 (verified tier). The highest-rated is PyThaiNLP/pythainlp at 93/100 with 1,117 stars and 1,203,313 monthly downloads. 2 of the top 10 are actively maintained.

Get all 73 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=nlp&subcategory=chinese-nlp-toolkits&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	PyThaiNLP/pythainlp Thai natural language processing in Python	93	Verified	1,117	Python
2	hankcs/HanLP Natural Language Processing for the next decade. Tokenization,...	77	Verified	36,209	Python
3	dongrixinyu/JioNLP 中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package...	70	Verified	3,802	Python
4	hankcs/pyhanlp 中文分词	68	Established	3,211	Python
5	jacksonllee/pycantonese Cantonese Linguistics and NLP	67	Established	400	Python
6	go-ego/gse Go efficient multilingual NLP and text segmentation; support English,...	65	Established	2,790	Go
7	baidu/lac 百度NLP：分词，词性标注，命名实体识别，词重要性	65	Established	3,992	C++
8	ownthink/Jiagu Jiagu深度学习自然语言处理工具知识图谱关系抽取中文分词词性标注命名实体识别情感分析新词发现关键词文本摘要文本聚类	64	Established	3,419	Python
9	SeanLee97/xmnlp xmnlp：提供中文分词, 词性标注, 命名体识别，情感分析，文本纠错，文本转拼音，文本摘要，偏旁部首，句子表征及文本相似度计算等功能	56	Established	1,297	Python
10	yongzhuo/Macropodus 自然语言处理工具Macropodus，基于Albert+BiLSTM+CRF深度学习网络架构，中文分词，词性标注，命名实体识别，新词发现，关键词，文本摘要...	54	Established	662	Python
11	NLPchina/ansj_seg ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典	51	Established	6,544	Java
12	linonetwo/segmentit 任何 JS 环境可用的中文分词包，fork from leizongmin/node-segment	50	Established	311	JavaScript
13	messense/jieba-rs The Jieba Chinese Word Segmentation Implemented in Rust	50	Established	902	Rust
14	jiaeyan/Jiayan 甲言，专注于古代汉语(古汉语/古文/文言文/文言)处理的NLP工具包，支持文言词库构建、分词、词性标注、断句和标点。Jiayan, the 1st...	50	Established	659	Python
15	monpa-team/monpa MONPA 罔拍是一個提供正體中文斷詞、詞性標註以及命名實體辨識的多任務模型	48	Emerging	247	Python
16	OpenPecha/pybo 🦜 NLP for Tibetan, in Python.	47	Emerging	39	Python
17	lionsoul2014/jcseg Jcseg is a light weight NLP framework developed with Java. Provide CJK and...	44	Emerging	920	Java
18	suminb/hanja 한글, 한자 라이브러리	43	Emerging	143	Python
19	yaoguangluo/Deta_Parser 快速中文分词分析word segmentation	43	Emerging	477	Java
20	hankcs/hanlp-lucene-plugin HanLP中文分词Lucene插件，支持包括Solr在内的基于Lucene的系统	43	Emerging	299	Java
21	XiaoMi/MiNLP XiaoMi Natural Language Processing Toolkits	43	Emerging	809	Scala
22	qinwf/jiebaR Chinese text segmentation with R. R语言中文分词（文档已更新 🎉...	43	Emerging	363	C++
23	notoriouslab/trad-zh-search trad-zh-search 可單獨搭配主流搜尋引擎，專門給繁體中文使用的繁體中文文本預處理工具 —— CKIP 分詞 + bigram 索引生成，附可選擇的領域字典系統	43	Emerging	15	Python
24	hankcs/multi-criteria-cws Simple Solution for Multi-Criteria Chinese Word Segmentation	42	Emerging	303	Python
25	jimichan/mynlp 一个生产级、高性能、模块化、可扩展的中文NLP工具包。（中文分词、平均感知机、fastText、拼音、新词发现、分词纠错、BM25、人名识别、命名实体、自定义词典）	42	Emerging	690	Java
26	smoothnlp/SmoothNLP 专注于可解释的NLP技术 An NLP Toolset With A Focus on Explainable Inference	42	Emerging	621	Java
27	houbb/opencc4j 🇨🇳Open Chinese Convert is an opensource project for conversion between...	41	Emerging	563	Java
28	KoichiYasuoka/UD-Kanbun Tokenizer POS-tagger and Dependency-parser for Classical Chinese	41	Emerging	71	Python
29	supercoderhawk/DeepLearning_NLP 基于深度学习的自然语言处理库	40	Emerging	159	Python
30	hankcs/ID-CNN-CWS Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese...	40	Emerging	133	Python
31	notAI-tech/deepsegment A sentence segmenter that actually works!	40	Emerging	304	Python
32	kirklin/go-swd Sensitive Words Detection 一个高性能的敏感词检测和过滤库，基于 Go...	39	Emerging	88	Go
33	houbb/segment The jieba-analysis tool for java.（基于结巴分词词库实现的更加灵活优雅易用，高性能的 java 分词实现。支持词性标注。）	38	Emerging	156	Java
34	StarCC0/starcc-py 简繁转换簡繁轉換 Python implementation of StarCC, the next generation of...	37	Emerging	71	Python
35	houbb/pinyin The high performance pinyin tool for java.(java 高性能中文转拼音工具。支持同音字。)	37	Emerging	297	Java
36	houbb/nlp-hanzi-similar The hanzi similar tool.(汉字相似度计算工具，中文形近字算法。可用于手写汉字识别纠正，文本混淆等。)	37	Emerging	290	Java
37	junchaoIU/QCNLP A Preprocessing & Parsing tool for Chinese Natural Language （一个高效的中文预处理与自然语言处理解析工具）	36	Emerging	4	Python
38	mxcoras/jieba-next Use Rust to Speed up jieba 高效、现代的中文分词库	33	Emerging	10	Python
39	google/budou Budou is an automatic organizer tool for beautiful line breaking in CJK...	33	Emerging	1,186	Python
40	KoichiYasuoka/SuPar-Kanbun Tokenizer POS-tagger and Dependency-parser for Classical Chinese	33	Emerging	19	Jupyter Notebook
41	cyd622/nlp-jieba 结巴中文分词（PHP 版本）：做最好的 PHP 中文分词、中文断词组件	31	Emerging	17	PHP
42	KoichiYasuoka/GuwenCOMBO Tokenizer POS-tagger and Dependency-parser for Classical Chinese	31	Emerging	15	Jsonnet
43	shibing624/crf-seg crf-seg:用于生产环境的中文分词处理工具，可自定义语料、可自定义模型、架构清晰，分词效果好。java编写。	31	Emerging	14	Java
44	bububa/jiagu Jiagu深度学习自然语言处理工具知识图谱关系抽取中文分词词性标注命名实体识别情感分析新词发现关键词文本摘要文本聚类	30	Emerging	22	Go
45	wittawatj/jtcc Java library to tokenize Thai text into a list of TCCs	30	Emerging	19	Java
46	KoichiYasuoka/SuPar-Kanbun-1.3.4 Tokenizer POS-tagger and Dependency-parser for Classical Chinese	27	Experimental	19	Jupyter Notebook
47	sdq/FenciMac 中文分词 Mac版	27	Experimental	10	C++
48	supercoderhawk/DeepNLP 基于深度学习的自然语言处理库	27	Experimental	38	Python
49	jamsinclair/budou-node Node.js port of Budou, an automatic organizer tool for beautiful line...	25	Experimental	5	JavaScript
50	jason2506/esapp An unsupervised Chinese word segmentation tool.	25	Experimental	13	C++
51	zxgineng/deepnlp 小时候练手的nlp项目	25	Experimental	13	Python
52	dogterbox/thai-word-segmentation Thai word segmentation using deep learning	24	Experimental	14	Jupyter Notebook
53	PyThaiNLP/Han-solo 🪿 Han-solo: Thai syllable segmenter	22	Experimental	9	Jupyter Notebook
54	bryanchw/Traditional-Chinese-Stopwords-and-Punctuations-Library Created a Python library specifically for Traditional Chinese stopwords and...	21	Experimental	8	Python
55	hope-data-science/chinese_NLP 中文自然语言处理	21	Experimental	11	R
56	limchiahooi/nlp-chinese This repo contains my Natural Language Processing (NLP) in Chinese project.	21	Experimental	11	Jupyter Notebook
57	mathsyouth/awesome-word-segmentation A curated list of resources dedicated to word segmentation	20	Experimental	12	—
58	jsrpy/Chinese-NLP-Jieba This is an introduction to Chinese words segmentation using Jieba.	20	Experimental	14	Jupyter Notebook
59	cxumol/jieba-wasm-html Fast Jieba Chinese text segmentation on browser without backend/NPM \|...	20	Experimental	33	JavaScript
60	shibing624/pinyin-tokenizer pinyintokenizer, 拼音分词器，将连续的拼音切分为单字拼音列表。	20	Experimental	31	Python
61	wchan757/Cantonese_Word_Segmentation Dictionary for Cantonese word segmentation	20	Experimental	38	—
62	Lapis-Hong/fast-xinci 新词发现 Chinese New Words Finder (c++ library).	19	Experimental	9	C++
63	gyatso736/-Tibetan-tokenizer- This Tibetan tokenizer based on Bi-LSTM+CRF methods, it was created with the...	19	Experimental	10	Python
64	JackHCC/Chinese-Tokenization 利用传统方法（N-gram，HMM等）、神经网络方法（CNN，LSTM等）和预训练方法（Bert等）的中文分词任务实现【The word...	18	Experimental	38	Python
65	NoHeartPen/Kanji2Hanzi This Project is used to convert Japanese Kanji to Simplifed Chinese character.	16	Experimental	41	Python
66	NicoACloutier/Hanzi.jl A Julia library to romanize Hanzi.	15	Experimental	—	Julia
67	Jyutt/jieba-hs Jieba中文分詞算法Haskell版本 Haskell Implementation of Jieba Chinese Segmentation Algorithm	13	Experimental	6	Haskell
68	yihong-chen/chinese-word-segmentation Simple chinese word segmentation with experiments on the PKU datatset	13	Experimental	8	Jupyter Notebook
69	wittawatj/ctwt Classifier-based Thai Word Tokenizer	13	Experimental	5	Java
70	sinostudy/pinyin Convert between different representations of Hànyǔ Pīnyīn.	13	Experimental	5	Clojure
71	bmwj/Tibetan_information_processing 藏文信息处理工具集（Tibetan_Information_Processing_Toolkit），其功能包含：生成完整的藏文字符集，智能识别藏文字符构件...	11	Experimental	5	Python
72	Ancastal/HSK-Character-Profiler HSK Character Profiler is a Python tool that analyzes Chinese character...	10	Experimental	1	Python
73	StarCC0/starcc0.github.io 简繁转换簡繁轉換 StarCC is the next generation of Simplified-Traditional Chinese...	10	Experimental	1	—

Comparisons in this category

HanLP and pyhanlp (77 vs 68)