JioNLP

中文 NLP 预处理、解析工具包,准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

What is JioNLP?

中文 NLP 预处理、解析工具包,准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

Overview of JioNLP

What it is

JioNLP is a Chinese NLP preprocessing and parsing toolkit. It provides accurate, efficient, and easy-to-use functions for various NLP tasks. The package is available via pip and is designed for NLP developers. It includes tools for text cleaning, information extraction, data augmentation, and more. The project is hosted on GitHub and licensed under Apache-2.0.

Key features

  • Time semantic parsing: extracts timestamps and durations from time-related text.
  • Key phrase extraction: extracts key phrases from a given text.
  • Location parsing: identifies province, city, county, and other administrative divisions from Chinese address strings.
  • ID card parsing: extracts and parses Chinese ID card numbers to reveal province, city, birth date, gender, and checksum.
  • Data augmentation: includes back-translation, homophone substitution, entity replacement, and other methods to augment text data.
  • Regular expression extraction and cleaning: extracts emails, URLs, phone numbers, money amounts, and cleans text by removing abnormal characters, HTML tags, and redundant characters.
  • Dictionary loading: provides stopwords, Chinese idioms, xiehouyu, and location dictionaries.

Use cases

JioNLP is suitable for Chinese NLP preprocessing pipelines, such as cleaning raw text, extracting structured information (time, location, ID, phone numbers), augmenting training data for machine learning models, and performing basic text analysis like key phrase extraction and pinyin conversion. It can be used in applications like data mining, information retrieval, and chatbot development.

Getting started

Install via pip: pip install jionlp After installation, import the package and explore its functions: import jionlp as jio print(jio.__version__) dir(jio) For detailed usage, refer to the repository README.

License and pricing

The project is open source under the Apache-2.0 license. It is free to use.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/dongrixinyujionlp.svg)](https://yunodb.com/tools/dongrixinyujionlp?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/dongrixinyujionlp?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/dongrixinyujionlp.svg" alt="Featured on YunoDB" height="20"></a>