-
-
Notifications
You must be signed in to change notification settings - Fork 274
The story of Underthesea
Vu Anh edited this page Jun 9, 2024
·
1 revision
Underthesea is a toolkit that supports the research and development of Vietnamese natural language processing. Underthesea was created in March 2017, in a context where Vietnam already had some good toolkits like vn.vitk and pyvi, but still lacked a complete, open-source, easy to install and use toolkit comparable to English counterparts like nltk, polyglot, and spacy.
- Underthesea is a tool that is easy to use, easy to install, and comes with comprehensive guides and documentation.
- Underthesea is open-source software, allowing everyone to use it freely for educational, research, and commercial purposes.
- Underthesea is always ready to support, with all issues being responded to quickly.
- Underthesea supports language processing tasks including text, speech, and handwritten image processing.
In the distant future,
- Underthesea will update with the latest research in natural language processing.
- Underthesea will serve as a bridge between Vietnamese NLP researchers. Through Underthesea, researchers can implement ideas, integrate datasets, and share the latest research results with the community.
[Update 2022]: Some famous tools for natural language processing HanLP 27.3k, stanza 6.4k, transformers 73.3k, flair 12.2k.