Updated time: 2023-03-08 11:59:46
Word Segmentation (WS), Part-of-Speech Tagging (POS) and Named Entity Recognition (NER) the three key techniques for natural language processing. Based on our home deep learning techniques, we developed an integrated package to conduct WS, POS and NER within one toolkit. For NER, it can extract named entities from the text and annotate their types automatically. Our system can recognize 11 general entity types and 7 numeral types, including: person, norp, facility, organization, gpe, location, product, event, work of art, law, language, date, time, percent, money, quantity, ordinal and cardinal.
Welcome to test our online system: https://ckip.iis.sinica.edu.tw/service/corenlp/.
- CkipTagger significantly surpasses Jieba system.
- Rich POS types: 61 POS types in total (https://github.com/ckiplab/ckiptagger/wiki/POS-Tags)
- Rich NER types: 11 general entity types and 7 numeral types (https://github.com/ckiplab/ckiptagger/wiki/Entity-Types)
- Support user-defined word list
- The technique was published on prestigious international conference on Artificial Intelligence – AAAI 2020 (https://arxiv.org/abs/1908.11046)

Fig1. Performance Comparison between CkipTagger and Jieba
05T-1081218
2020-01-02
Know-how
- Big-data Opinion Analysis
- Language Understanding
- Intelligent Agent
- Chatbot
- Commodity Intelligence System
Wei-Yun Ma、Peng-Hsuan Li
If you are interested in this technology, please fill in the information on the webpage under the manufacturer option (Request for Technology Licensing, Material Transfer, or Sponsored Research) on the website of this office

Fig2. Usage Example of CkipTagger

Integrated Toolkit of Chinese Word Segmentation, Part of Speech Tagging and Named Entity Recognition (CkipTagger)