kuan-wang/graph-soft-counter
[ICLR 2022] GNN is a Counter? Revisiting GNN for Question Answering
This project helps researchers and practitioners in natural language processing (NLP) to improve the accuracy of automated question-answering systems. It takes in a question and a relevant knowledge graph, and outputs a more accurate answer to the question by better understanding how entities in the question relate to the knowledge graph. This is useful for anyone building or evaluating advanced AI systems that need to reason with both text and structured knowledge.
No commits in the last 6 months.
Use this if you are working on question-answering tasks that require reasoning over both text and knowledge graphs, and you want to achieve higher accuracy.
Not ideal if your question-answering needs are simple lookup-based or if you don't have access to structured knowledge graphs.
Stars
10
Forks
5
Language
Python
License
MIT
Category
Last pushed
Apr 11, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kuan-wang/graph-soft-counter"
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)