GiNZA

GiNZA is an open-source Japanese NLP library based on Universal Dependencies, providing tokenization, part-of-speech tagging, dependency parsing, named entity recognition, and sentence segmentation. The current version (5.2.0) requires Python >=3.8 and is released via GitHub (megagonlabs/ginza) and PyPI. It uses the spaCy pipeline internally and offers a robust model for Japanese text processing.