# NLPchina/ansj_seg

ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典

Repository: https://github.com/NLPchina/ansj_seg
Canonical: https://ross.abutalabs.com/products/ansj_seg
Language: Java
License: Apache-2.0
License Family: permissive
Topics: nlp, chinese, ansj, java
Last push: 2023-11-19T06:15:23+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": 5110, "days_push": 1018, "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 6517, forks 2267 (observed 2026-08-28T04:09:44.872256+00:00)

## What it is
A Java library for Chinese word segmentation based on n-Gram+CRF+HMM, achieving ~2 million characters/second with 96%+ accuracy. It also provides Chinese name recognition, part-of-speech tagging, custom dictionaries, keyword extraction, and automatic summarization.

## Use cases
- segment chinese text into words
- tokenize chinese sentences in java
- recognize chinese person names in text
- add custom domain dictionary to a chinese tokenizer
- extract keywords from chinese documents
- generate automatic summaries of chinese text
- tag parts of speech for chinese words

## When to choose
- you need fast, high-accuracy chinese word segmentation on the JVM
- you want user-defined dictionaries and name recognition out of the box
- your project is Java/Maven-based and needs a pure-Java ict-class segmentation solution

## When to avoid
- you need segmentation for languages other than chinese
- you want state-of-the-art neural (LSTM/transformer) segmentation models
- you need a library with frequent updates and active community support

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, parser
- domain: localization
- platform: jvm
- tags: chinese-word-segmentation, part-of-speech-tagging, named-entity-recognition, custom-dictionary, keyword-extraction, text-summarization, natural-language-processing

## Member repositories
- NLPchina/ansj_seg (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:44.872256+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 2026-08-29T17:44:25.933012+00:00, confidence not recorded.
  - readme: https://github.com/NLPchina/ansj_seg (fetched 2026-08-28T04:09:44.872256+00:00, sha 878c96754bdf)
- Data as of 2026-08-30T08:39:29.467469+00:00.