# thunlp/THULAC-Python

An Efficient Lexical Analyzer for Chinese

Repository: https://github.com/thunlp/THULAC-Python
Canonical: https://ross.abutalabs.com/products/thulac-python
Language: Python
License: MIT
License Family: permissive
Topics: chinese-nlp
Last push: 2022-01-31T08:49:17+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3760, "days_push": 1675, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2085, forks 332 (observed 2026-08-28T04:06:11.874365+00:00)

## What it is
THULAC is a Chinese lexical analysis toolkit from Tsinghua University's NLP lab that performs Chinese word segmentation and part-of-speech tagging. It offers a Python library and command-line interface, trained on a large manually annotated corpus with high accuracy and fast processing speeds.

## Use cases
- segment chinese text into words
- part-of-speech tagging for chinese sentences
- batch tokenize a text file of chinese content
- preprocess chinese text for nlp pipelines
- convert traditional chinese to simplified before segmentation
- apply a custom user dictionary during chinese tokenization

## When to choose
- you need fast, accurate chinese word segmentation with pos tagging in python
- you want a battle-tested tokenizer with a large trained model
- you need command-line batch segmentation of chinese text files

## When to avoid
- you need segmentation for languages other than chinese
- you require actively maintained software with recent updates
- you need deep learning based or transformer-based tokenization

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, parser
- domain: -
- platform: python, cross-platform, cli
- tags: chinese-word-segmentation, part-of-speech-tagging, lexical-analysis, tokenization, natural-language-processing, chinese-nlp, text-processing

## Member repositories
- thunlp/THULAC-Python (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:11.874365+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:55:51.315894+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/THULAC-Python (fetched 2026-08-28T04:06:11.874365+00:00, sha cd4ddc2cdce8)
- Data as of 2026-08-30T08:39:29.467469+00:00.