Cartus/DCGCN
Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning (authors' MXNet implementation for the TACL19 paper)
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.
Stars
77
Forks
8
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
kyzhouhzau/NLPGNN
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and...
IndexFziQ/GNN4NLP-Papers
A list of recent papers about Graph Neural Network methods applied in NLP areas.
qipeng/gcn-over-pruned-trees
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (authors' PyTorch...
kenqgu/Text-GCN
A PyTorch implementation of "Graph Convolutional Networks for Text Classification." (AAAI 2019)
daiquocnguyen/Graph-Transformer
Universal Graph Transformer Self-Attention Networks (TheWebConf WWW 2022) (Pytorch and Tensorflow)