graph-2-text
A PyTorch implementation combining Graph Convolutional Networks with OpenNMT-py for structured data to text generation.
What is graph-2-text?
Graph-2-text is a PyTorch-based research implementation that combines Graph Convolutional Networks (GCNs) with the OpenNMT-py library to generate natural language text from structured graph data. It addresses the challenge of converting graph-structured information, such as knowledge graphs or semantic representations, into coherent textual descriptions. The model is designed for structured data-to-text generation tasks, providing a neural approach that leverages graph encoders.
Researchers and practitioners in natural language generation, computational linguistics, and graph neural networks who need to generate text from structured data like knowledge graphs or semantic representations.
It offers a reproducible, extensible codebase that integrates graph neural networks with sequence-to-sequence models, specifically tailored for structured data-to-text tasks. The implementation provides configurable GCN architectures and supports research experimentation with copy mechanisms and pre-trained embeddings.
Overview
Graph to sequence implemented in Pytorch combining Graph convolutional networks and opennmt-py
Use Cases
Best For
- Generating textual descriptions from knowledge graphs or semantic networks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
