- homepage: https://opennlp.apache.org/
- link: https://github.com/apache/opennlp
- author: Apache
- link: https://github.com/fxsjy/jieba
- author: Sun Junyi
- homepage: http://www.ltp-cloud.com/intro / http://ltp.ai/
- author: HIT-SCIR
- navigation: pyltp, intro
- blog: 语言技术平台(LTP)推出 v4.2 版本!
- link: https://github.com/hankcs/HanLP/tree/1.x
- homepage: http://hanlp.com/
- author: hankcs (Han He)
- navigation: pyhanlp, install, pos meaning, add custom words
- link: https://github.com/stanfordnlp/stanza
- author: Stanford NLP
- note: a python nlp library for 60+ human languages.
- link: https://github.com/fastnlp/fastHan
- author: fastnlp group
- note: fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具,像spacy一样调用方便.
- extra: fastNLP.
- link: https://github.com/lancopku/pkuseg-python
- author: LancoPKU
- note: a toolkit for multi-domain Chinese word segmentation.
- homepage: https://ai.tencent.com/ailab/nlp/texsmart/zh/index.html
- author: 腾讯AI Lab-自然语言处理团队
- paper: TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
- note: 一套自然语言理解工具与服务, 用以对中文和英文两种语言的文本进行词法、句法和语义分析。 除了支持分词、词性标注、命名实体识别(NER)、句法分析、语义角色标注、文本分类、文本匹配、文本规范化(自动恢复英文大小写)等常见功能外, TexSmart还提供细粒度命名实体识别、语义联想、深度语义表达等特色功能。
- link: https://github.com/jiaeyan/Jiayan
- author: Jiajie Ya
- note: NLP tools for ancient Chinese.
- link: https://github.com/sloria/TextBlob
- web: https://textblob.readthedocs.io/en/dev/
- author: Steven Loria
- note: a Python (2 and 3) library for processing textual data.
- link: https://github.com/tsroten/zhon
- web: https://zhon.readthedocs.io/en/latest/#
- author: Thomas Roten
- note: constants used in Chinese text processing.
- link: https://github.com/fastcws/fastcws
- author: fastcws
- note: 轻量级高性能中文分词项目.
- link: https://github.com/tmu-nlp/nccp
- author: zchen0420
- note: two efficient constituency parsing algorithms.