https://github.com/howl-anderson/microtagger
一个微型的用于提取 Part-Of-Speech (POS) 的 Python 包 | A micro python library for NLP Tagger of Part-Of-Speech (POS)
https://github.com/howl-anderson/microtagger
hmm-viterbi-algorithm nlp nlp-parsing part-of-speech-tagger
Last synced: 4 months ago
JSON representation
一个微型的用于提取 Part-Of-Speech (POS) 的 Python 包 | A micro python library for NLP Tagger of Part-Of-Speech (POS)
- Host: GitHub
- URL: https://github.com/howl-anderson/microtagger
- Owner: howl-anderson
- Created: 2018-06-28T14:05:06.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2018-09-13T09:31:26.000Z (almost 7 years ago)
- Last Synced: 2025-01-21T21:47:03.503Z (6 months ago)
- Topics: hmm-viterbi-algorithm, nlp, nlp-parsing, part-of-speech-tagger
- Language: Python
- Homepage:
- Size: 14.8 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.en-US.md
Awesome Lists containing this project
README
[中文版本的 README](README.md)
------------------------------
# MicroTagger
A micro python library for NLP Tagger of Part-Of-Speech (POS)
# Installation
```bash
pip install -r requirements.txt
```
# Python version
Only test by using Python3
# Usage
```python
#!/usr/bin/env python
from MicroTagger.hmm import HMMTagger
hmm_tagger = HMMTagger.load()
result = hmm_tagger.predict("知识 就是 力量 。")
print(result)
```
Output:
```text
知识/m 就是/d 力量/n 。/wj
```
# Performance
| ID | Model Name | Accuracy |
|:---|:-----------------------------|:---------|
| 1 | Most Frequent Class Baseline | 0.83703 |
| 2 | HMM | 0.92339 |
# Reference
[Speech and Language Processing > Part-of-Speech Tagging]([](https://web.stanford.edu/~jurafsky/slp3/10.pdf))