NLPIR-team/NLPIR

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3474 stars · 1996 forks observed · 2026-08-28

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

NLPIR is a Chinese natural language processing platform (formerly ICTCLAS) providing an SDK with around twenty text analysis functions including word segmentation, POS tagging, named entity recognition, keyword extraction, classification, and summarization. The repository bundles the SDK, license files, a Lucene integration, a no-code document parsing client, and related research papers.

Use cases

• segment chinese text into words
• extract keywords from chinese documents
• named entity recognition for chinese text
• integrate chinese tokenization into lucene search
• classify and summarize chinese documents without coding
• build knowledge graphs from chinese text

When to choose

• you need mature chinese word segmentation (ICTCLAS) with multi-language SDK bindings
• you want a desktop client to analyze documents without writing code
• you need chinese NLP integrated into a Lucene/Solr search pipeline

When to avoid

• you need a permissively licensed library - licensing terms are restrictive and license files require periodic renewal
• you need state-of-the-art transformer-based NLP rather than classical statistical methods
• you work primarily with non-Chinese text

Facets

library · maturity active

nlp parser search-engine sdk big-data developer-tools cross-platform windows python jvm cpp chinese-word-segmentation ictclas text-mining knowledge-graph lucene-integration chinese-nlp natural-language-processing linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NLPIR-team/NLPIR")