joshchang1112/bert_gnn_arxiv
Multi-class Classification with fine-tuned BERT & GNN
This project helps machine learning researchers improve the accuracy of classifying research papers by topic. It takes a dataset of scientific papers, including their text and citation network, and outputs a highly accurate model that can categorize new papers. This is designed for machine learning scientists or data scientists working with academic or research document classification.
No commits in the last 6 months.
Use this if you need to classify large collections of research papers into multiple categories with state-of-the-art accuracy, leveraging both text content and citation links.
Not ideal if you are not familiar with PyTorch or deep learning frameworks, or if your dataset does not involve interconnected text documents like citation networks.
Stars
46
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 07, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/joshchang1112/bert_gnn_arxiv"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
fidelity/textwiser
[AAAI 2021] TextWiser: Text Featurization Library
RandolphVI/Multi-Label-Text-Classification
About Muti-Label Text Classification Based on Neural Network.
ThilinaRajapakse/pytorch-transformers-classification
Based on the Pytorch-Transformers library by HuggingFace. To be used as a starting point for...
ntumlgroup/LibMultiLabel
A library for multi-class and multi-label classification
xuyige/BERT4doc-Classification
Code and source for paper ``How to Fine-Tune BERT for Text Classification?``