# graph4ai/graph4nlp

Graph4nlp is the library for the easy use of Graph Neural Networks for NLP. Welcome to visit our DLG4NLP website (https://dlg4nlp.github.io/index.html) for various learning resources!

Repository: https://github.com/graph4ai/graph4nlp
Canonical: https://ross.abutalabs.com/products/graph4nlp
Language: Python
License: Apache-2.0
License Family: permissive
Topics: nlp, pytorch, natural-language-processing, deep-learning, machine-learning, graph-neural-networks
Last push: 2024-06-24T03:38:13+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2239, "days_push": 800, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1690, forks 206 (observed 2026-08-28T04:05:22.492120+00:00)

## What it is
Graph4NLP is a Python library for applying Graph Neural Networks to Natural Language Processing tasks, built on DGL and PyTorch. It provides full implementations of state-of-the-art models plus flexible interfaces for building custom models with whole-pipeline support.

## Use cases
- apply graph neural networks to NLP problems
- build text classification models with GNNs
- implement semantic parsing with graph-based models
- run machine translation using graph neural networks
- build question answering models with graph representations
- research deep learning on graphs for NLP
- convert text into graph structures for learning

## When to choose
- you want ready-made GNN models for NLP tasks
- you need a pipeline from text to graph to model output
- you are doing research at the intersection of graphs and NLP
- you want to build on DGL with NLP-specific abstractions

## When to avoid
- you need a general-purpose GNN library without NLP focus
- you want actively developed tooling with frequent releases
- you need transformer-only pipelines without graph structures
- you require production-grade support and long-term maintenance guarantees

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: graph-neural-networks, pytorch, dgl, research, natural-language-processing

## Member repositories
- graph4ai/graph4nlp (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:22.492120+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 2026-08-30T03:38:21.829020+00:00, confidence not recorded.
  - readme: https://github.com/graph4ai/graph4nlp (fetched 2026-08-28T04:05:22.492120+00:00, sha 150c66d9cc14)
- Data as of 2026-08-30T08:39:29.467469+00:00.