# Chinese-Text-Classification-Pytorch

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

Repository: https://github.com/649453932/Chinese-Text-Classification-Pytorch
Canonical: https://ross.abutalabs.com/products/chinese-text-classification-pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2020-09-23T11:28:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2611, "days_push": 2170, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5728, forks 1254 (observed 2026-08-28T04:09:28.295748+00:00)

## What it is
A PyTorch-based collection of ready-to-run Chinese text classification models including TextCNN, TextRNN, FastText, TextRCNN, BiLSTM with attention, DPCNN, and Transformer, plus a companion repo with BERT/ERNIE classifiers. It ships with a 200k-sample THUCNews news headline dataset across 10 categories and works out of the box.

## Use cases
- classify chinese news headlines into categories
- train a textcnn model on chinese text
- compare text classification model architectures in pytorch
- fine-tune bert for chinese text classification
- run text classification experiments on thucnews dataset
- learn how text classification models work in pytorch

## When to choose
- you need a working baseline for Chinese text classification with minimal setup
- you want to benchmark classic architectures like TextCNN, TextRNN, or DPCNN
- you want a labeled Chinese dataset to experiment with

## When to avoid
- you need multilingual or non-Chinese text classification
- you need production-grade training pipelines with modern tooling
- you need actively maintained code - the last release was 2020

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: text-classification, pytorch, chinese-nlp, textcnn, bilstm, transformer, bert, thucnews, natural-language-processing

## Member repositories
- 649453932/Chinese-Text-Classification-Pytorch (main) score 32
- 649453932/Bert-Chinese-Text-Classification-Pytorch (plugin) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.295748+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 2026-08-29T17:53:24.120332+00:00, confidence not recorded.
  - readme: https://github.com/649453932/Chinese-Text-Classification-Pytorch (fetched 2026-08-28T04:09:28.295748+00:00, sha 5dd0c7071b71)
- Data as of 2026-08-30T08:39:29.467469+00:00.