taishi-i/nagisa
A Python library using RNNs to perform Japanese word segmentation and part-of-speech tagging.

Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
Nagisa is a neural-network-based Japanese tokenizer and POS tagger. It uses character-level and word-level features in its segmentation model, and incorporates tag dictionary information in its POS-tagging model. The tool is designed as a simple, easy-to-use Python module for processing Japanese text.