# HIT-SCIR/ltp

Language Technology Platform

Repository: https://github.com/HIT-SCIR/ltp
Canonical: https://ross.abutalabs.com/products/ltp
Homepage: http://ltp.ai
Language: Python
License Family: other
Topics: nlp, natural-language-processing, chinese-nlp, machine-learning
Last push: 2026-03-11T11:57:37+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 8, longevity 100
- inputs: {"age_days": 5572, "days_push": 175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5259, forks 1060 (observed 2026-08-28T04:09:13.816198+00:00)

## What it is
LTP (Language Technology Platform) is an open-source neural NLP toolkit for Chinese supporting word segmentation, POS tagging, NER, dependency parsing, semantic dependency parsing, and semantic role labeling via a shared multi-task pre-trained model. It offers Python and Rust packages, pre-trained models, and an optional server mode.

## Use cases
- segment chinese text into words
- pos tagging for chinese sentences
- named entity recognition in chinese text
- dependency parsing of chinese sentences
- semantic role labeling for chinese
- chinese nlp pipeline for text analysis

## When to choose
- you need accurate Chinese-specific lexical, syntactic, or semantic analysis
- you want a single multi-task model instead of one model per task
- you prefer a pip-installable Python toolkit with pretrained models

## When to avoid
- you need multilingual NLP beyond Chinese
- you need a permissive license - the repo lists no license
- you only need general-purpose LLM features rather than classical NLP tasks

## Facets
- artifact type: library
- maturity: active
- function: nlp, machine-learning, parser
- domain: machine-learning
- platform: python, rust, cross-platform
- tags: chinese-nlp, word-segmentation, pos-tagging, dependency-parsing, semantic-role-labeling, named-entity-recognition, multitask-learning, natural-language-processing

## Member repositories
- HIT-SCIR/ltp (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:13.816198+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 2026-08-29T17:59:31.138467+00:00, confidence not recorded.
  - readme: https://github.com/HIT-SCIR/ltp (fetched 2026-08-28T04:09:13.816198+00:00, sha b6b73b7a7060)
  - homepage: http://ltp.ai (fetched 2026-08-29T08:54:31.799711+00:00, sha da8f67878f5b)
  - site_page: https://ltp.ai/docs/index.html (fetched 2026-08-29T08:54:31.808844+00:00, sha 52988a0f9a67)
  - registry_pypi: https://pypi.org/pypi/ltp/json (fetched 2026-08-29T08:54:31.812258+00:00, sha 5813bc0ef1d7)
  - site_page: https://ltp.ai/faq.html (fetched 2026-08-29T08:54:31.810551+00:00, sha 71d578181a44)
- Data as of 2026-08-30T08:39:29.467469+00:00.