# koth/kcws

Deep Learning Chinese Word Segment

Repository: https://github.com/koth/kcws
Canonical: https://ross.abutalabs.com/products/kcws
Language: C++
License Family: other
Topics: nlp, deep-learning, chinese-text-segmentation, tensorflow, pos-tagger
Last push: 2018-05-18T03:22:58+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3569, "days_push": 3029, "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 2069, forks 630 (observed 2026-08-28T04:06:10.253475+00:00)

## What it is
A deep learning Chinese word segmentation toolkit implemented in C++ with TensorFlow, supporting BiLSTM+CRF and IDCNN+CRF models, plus part-of-speech tagging. It includes training pipelines (word2vec, data generation, model export) and a backend web service for segmentation.

## Use cases
- segment chinese text into words
- chinese word segmentation with deep learning
- tag part of speech for chinese sentences
- train a custom chinese segmentation model
- run a segmentation web service api
- recognize company names in chinese text
- add a custom dictionary to segmentation

## When to choose
- you need Chinese word segmentation or POS tagging with neural models
- you want to train your own segmentation model on custom annotated corpora
- you need a C++ backend service for segmentation with custom dictionary support

## When to avoid
- you need actively maintained software or a permissive license (no license, last release 2018)
- you need segmentation for languages other than Chinese
- you want a pure Python or pip-installable solution

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning, http-server
- domain: machine-learning, deep-learning
- platform: cpp, python
- tags: chinese-word-segmentation, bilstm-crf, idcnn-crf, pos-tagger, tensorflow, word2vec, custom-dictionary, natural-language-processing, chinese-text-segmentation, linux

## Member repositories
- koth/kcws (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.253475+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 2026-08-30T02:56:45.846617+00:00, confidence not recorded.
  - readme: https://github.com/koth/kcws (fetched 2026-08-28T04:06:10.253475+00:00, sha c81929776737)
- Data as of 2026-08-30T08:39:29.467469+00:00.