FudanNLP/fastHan
A BERT-based multi-task toolkit for Chinese NLP supporting word segmentation, POS tagging, dependency parsing, and NER.
Not currently ranked — collecting fresh signals.
star history
fastHan is a Chinese natural language processing toolkit built on fastNLP and PyTorch that leverages a BERT-based joint model to simultaneously handle multiple tasks including word segmentation, part-of-speech tagging, dependency parsing, and named entity recognition. The model was trained on 15 corpora and also supports ancient Chinese NLP tasks. It aims to provide spaCy-like ease of use for Chinese NLP applications.
Frequently asked
- What is FudanNLP/fastHan?
- A BERT-based multi-task toolkit for Chinese NLP supporting word segmentation, POS tagging, dependency parsing, and NER.
- Is fastHan open source?
- Yes — FudanNLP/fastHan is open source, released under the Apache-2.0 license.
- What language is fastHan written in?
- FudanNLP/fastHan is primarily written in Python.
- How popular is fastHan?
- FudanNLP/fastHan has 761 stars on GitHub.
- Where can I find fastHan?
- FudanNLP/fastHan is on GitHub at https://github.com/FudanNLP/fastHan.