# Tencent/NeuralNLP-NeuralClassifier

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Repository: https://github.com/Tencent/NeuralNLP-NeuralClassifier
Canonical: https://ross.abutalabs.com/products/neuralnlp-neuralclassifier
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-11-18T08:56:25+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 52, release rhythm 35, longevity 100
- inputs: {"age_days": 2617, "days_push": 288, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1922, forks 404 (observed 2026-08-28T04:05:55.277578+00:00)

## What it is
NeuralClassifier is a PyTorch-based open-source toolkit for neural text classification, with a focus on hierarchical multi-label classification. It provides many text encoders such as FastText, TextCNN, TextRNN, RCNN, VDCNN, DPCNN, DRNN, AttentiveConvNet, and Transformer, and also supports binary and multi-class classification.

## Use cases
- train a hierarchical multi-label text classifier
- classify documents into a category tree
- run multi-label text classification with pytorch
- compare text encoders like TextCNN and Transformer for classification
- build a binary or multi-class text classifier
- experiment with HMCN for hierarchical classification

## When to choose
- you need hierarchical or multi-label text classification out of the box
- you want to benchmark many classic text classification encoders in one toolkit
- you prefer a PyTorch-based, config-driven training pipeline

## When to avoid
- you need modern pretrained transformer fine-tuning (e.g., BERT) as the primary workflow
- you need tasks beyond text classification such as NER or QA
- you want a production serving system rather than a training toolkit

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp
- domain: machine-learning, deep-learning
- platform: python
- tags: text-classification, hierarchical-classification, multi-label, pytorch, text-encoders, toolkit, natural-language-processing

## Member repositories
- Tencent/NeuralNLP-NeuralClassifier (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.277578+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 2026-08-30T03:09:40.116657+00:00, confidence not recorded.
  - readme: https://github.com/Tencent/NeuralNLP-NeuralClassifier (fetched 2026-08-28T04:05:55.277578+00:00, sha 124da949e737)
- Data as of 2026-08-30T08:39:29.467469+00:00.