# baidu/lac

百度NLP：分词，词性标注，命名实体识别，词重要性

Repository: https://github.com/baidu/lac
Canonical: https://ross.abutalabs.com/products/lac
Language: C++
License: Apache-2.0
License Family: permissive
Topics: word-segmentation, part-of-speech-tagger, named-entity-recognition, chinese-word-segmentation, chinese-nlp, lexical-analysis, python, java
Last push: 2021-05-25T10:46:36+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2984, "days_push": 1926, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4001, forks 592 (observed 2026-08-28T04:08:32.052802+00:00)

## What it is
LAC (Lexical Analysis of Chinese) is Baidu's deep-learning-based Chinese lexical analysis toolkit that jointly performs word segmentation, part-of-speech tagging, named entity recognition, and word importance ranking. It offers Python, Java, C++, and Android interfaces with a lightweight 2MB mobile model and high-throughput CPU inference.

## Use cases
- segment chinese text into words
- tag part of speech for chinese sentences
- recognize named entities like person, location, and organization names in chinese text
- rank word importance in chinese queries
- run chinese nlp preprocessing on mobile devices
- integrate chinese tokenization into a java or c++ application

## When to choose
- you need accurate chinese word segmentation, POS tagging, or NER with a proven deep-learning model
- you need fast cpu inference or a tiny model for mobile deployment
- you want a customizable user dictionary to intervene in model predictions

## When to avoid
- you need lexical analysis for languages other than chinese
- you need actively maintained software with recent releases
- you need full nlp pipelines beyond lexical analysis such as parsing or generation

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, parser
- domain: -
- platform: python, cpp, jvm, cross-platform
- tags: chinese-word-segmentation, part-of-speech-tagger, named-entity-recognition, lexical-analysis, paddlepaddle, word-importance, natural-language-processing, chinese-nlp, android

## Member repositories
- baidu/lac (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:32.052802+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 2026-08-29T18:24:07.771559+00:00, confidence not recorded.
  - readme: https://github.com/baidu/lac (fetched 2026-08-28T04:08:32.052802+00:00, sha 44b5c9053084)
- Data as of 2026-08-30T08:39:29.467469+00:00.