NLPchina/ansj_seg

Health v2 · maintenance only

Adoption not part of the score

6517 stars · 2267 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity maintenance

nlp parser localization jvm chinese-word-segmentation part-of-speech-tagging named-entity-recognition custom-dictionary keyword-extraction text-summarization natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NLPchina/ansj_seg")