Cartus/DCGCN

Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning (authors' MXNet implementation for the TACL19 paper)

37
/ 100
Emerging

This project offers an implementation of a deep learning model designed for advanced natural language processing tasks. It takes structured linguistic representations, such as Abstract Meaning Representation (AMR) graphs or syntax trees, and transforms them into natural language text. Researchers and practitioners in natural language generation and machine translation would use this to build systems that convert complex semantic or syntactic structures into coherent sentences.

No commits in the last 6 months.

Use this if you are a researcher or developer working on converting complex graph-based linguistic structures into natural language sentences, particularly for AMR-to-Text generation or syntax-based machine translation.

Not ideal if you need a general-purpose text generation tool or if your primary interest is in traditional sequence-to-sequence tasks without explicit graph structures.

natural-language-generation machine-translation computational-linguistics semantic-parsing graph-neural-networks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

77

Forks

8

Language

Python

License

MIT

Last pushed

Mar 25, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Cartus/DCGCN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.